← FlowlinesCONTENT HISTORY

Update to Flowlines

Snapshot Oct 24, 2026 · 13:14 UTC · version 0.4.1

Collection source: downloaded plugin package. These snapshots do not have a confirmed matching collection source. Differences in file lists alone do not establish changes to the package.

WHAT CHANGED

Instructions updated for flowlines-release-check

Full description — Now says: an MCP server release changed session outcomes in Flowlines - compare sessions, success rates, intents, cost, and signals before and after a deploy over the...

Observed in instructions or declared skills. Runtime behavior has not been tested.

Save Flowlines and check future changes in Following.

Up to 3 plugins free · no card required.

All fields and original values.

Full description

Before

Sep 30, 2026 · 23:10 UTC

a release of an agent changed its outcomes in Flowlines - compare sessions, success rates, intents, cost, and signals before and after a deploy over the Flowlines MCP server. Use when the user asks whether a deploy, prompt change, or new...

After

Oct 24, 2026 · 13:14 UTC

an MCP server release changed session outcomes in Flowlines - compare sessions, success rates, intents, cost, and signals before and after a deploy over the Flowlines MCP server. Use when the user asks whether a deploy, prompt change, or...

Skill instructions

Before

Sep 30, 2026 · 23:10 UTC

a release of an agent changed its outcomes in Flowlines - compare sessions, success rates, intents, cost, and signals before and after a deploy over the Flowlines MCP server. Use when the user asks whether a deploy, prompt change, or new...

After

Oct 24, 2026 · 13:14 UTC

an MCP server release changed session outcomes in Flowlines - compare sessions, success rates, intents, cost, and signals before and after a deploy over the Flowlines MCP server. Use when the user asks whether a deploy, prompt change, or...

Supporting files

Before

Sep 30, 2026 · 23:10 UTC

[{"relative_path":"agents/openai.yaml","size_in_bytes":227}]

After

Oct 24, 2026 · 13:14 UTC

[{"relative_path":"agents/openai.yaml","size_in_bytes":234}]

Compare saved observations

Download comparison JSON

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -1,23 +1,32 @@
 ---
 name: flowlines-release-check
-description: Check whether a release of an agent changed its outcomes in Flowlines - compare sessions, success rates, intents, cost, and signals before and after a deploy over the Flowlines MCP server. Use when the user asks whether a deploy, prompt change, or new version regressed or improved anything, or wants a go/no-go after shipping.
+description: Check whether an MCP server release changed session outcomes in Flowlines - compare sessions, success rates, intents, cost, and signals before and after a deploy over the Flowlines MCP server. Use when the user asks whether a deploy, prompt change, or new version regressed or improved anything, or wants a go/no-go after shipping. Do not use for a general review of the namespace (flowlines-weekly-review), one failing session (flowlines-investigate-session), or missing data (flowlines-doctor).
 ---
 
 # Flowlines release check
 
 Answer "did the last release change anything?" with numbers that have the right denominators, evidence from real sessions, and an honest statement of what cannot be known yet.
 
+## Tool discipline
+
+- Answer from the Flowlines MCP server first. It holds the data this skill works on, and every step below is written for its tools.
+- Use the Flowlines app, a browser, or web search only when the server cannot provide something the question needs, or when the user asks for it. Say that you are doing so and why. Never use them for data the server exposes, and never as a first move.
+- When part of the question stays unanswered, say so in the answer and list it in `unmet_needs` of `report_outcome`, with a pointer to where the user can look.
+- Match the effort to the question. For a plain question, make the minimum calls (`get_workspace`, `get_context`, then the one or two tools that answer it), answer, and `report_outcome`. Run the full procedure below only when the user asks for a release check or a go/no-go, and skip `save_note` and evidence sessions unless the procedure runs in full or the user asks for them.
+- If authentication is required, or a generic MCP error (such as `-32603`) repeats on one read-only check, use `flowlines-doctor` when available for connection recovery before further data calls. Client diagnostics and native sign-in are allowed for this repair. After verification, resume the original request with the same namespace, range, and `user_intent`.
+- If `flowlines-doctor` is unavailable, use only the failing client's connection status and native reconnect action. Reconnect once only when that client reports an authentication problem; leave browser consent to the user, then verify with one read-only call. If the action is unavailable, give the user the reconnect step in their client and wait for completion. For an unexplained generic error or failed verification, stop data calls, give the user the error and a pointer to Flowlines support. Do not access Flowlines infrastructure or present unavailable data as empty.
+
 ## Conventions for every Flowlines tool call
 
-- Every tool takes `reason` and `user_intent`. Keep `user_intent` identical across the conversation, for example "Check whether the 2026-09-01 release of the support agent regressed outcomes".
+- Every tool takes `reason` and `user_intent`. Keep `user_intent` identical across the conversation, for example "Check whether the 2026-09-01 release of the support MCP server regressed session outcomes".
 - Start with `get_workspace` once, then `get_context` for the namespace. Read pinned notes: a known evaluator artifact or ingestion gap changes how a comparison reads.
 - Quote the minimum from sessions and mask identifiers. Prefer aggregates.
 - End with `report_outcome` as the last tool call.
 
 ## Inputs
 
-1. The agent. `list_agents` shows the names Flowlines observes; use the exact name in filters.
-2. The release boundary as an ISO 8601 timestamp. Take it from the user, the deploy log, or the release list in the Flowlines app under Versions. Flowlines records a release either from a reported agent version or from a detected prompt change; the app's release receipt shows which.
+1. The MCP server. `list_agents` shows the service names Flowlines observes; use the exact name in `agent_name` filters.
+2. The release boundary as an ISO 8601 timestamp. Take it from the user or the deploy log. If neither gives it, the release list in the Flowlines app under Versions has it and the MCP server does not; read it there or ask the user. Flowlines records a release either from a reported version or from a detected prompt change; the app's release receipt shows which.
 3. The comparison window. Default to the same number of days on each side of the boundary, at least 3 and at most 14, so both sides have comparable traffic. Say when the after-window is still short.
 
 ## Steps
@@ -25,10 +34,10 @@
 1. `get_changes_since` with `since` set to the release boundary. This gives the after-side activity, outcomes, signals, and pinned notes in one call.
 2. Build the two windows from day buckets. `aggregate_sessions` only accepts trailing ranges that end now (`24h`, `7d`, `30d`, `90d`, `all`), so any range you pick contains post-release activity. Query the smallest range that covers both windows with `group_by: ["day"]` and metrics `session_count`, `user_count`, `success_count`, `failure_count`, `total_cost_usd`, `unanalyzed_count`, filtered by `agent_name`. Assign each day bucket to the before or after window yourself. The deployment day is mixed: exclude it from both windows unless the boundary falls at the start of the day, and say which choice you made. Day buckets cannot represent a boundary inside a day exactly; say so, and if that precision matters use `list_sessions` with `from` and `to` around the boundary for counts on that day only.
 3. Compute rates from the summed counts, never by averaging per-day or per-group rates: success rate for a window is the sum of `success_count` divided by the sum of `success_count` and `failure_count` across its days. A status-grouped query is not a shortcut, because each status group has a rate of 0 or 100 percent by construction. `get_metric_definition` for `success_rate` and any other rate you report, and apply the sample floor to the window's combined denominator; below it, report counts and say the rate is not yet meaningful. Sessions in the after-window are still being analysed, so a high `unanalyzed_count` makes the after-side rate provisional.
-4. Find what moved: `aggregate_sessions` for the same covering range with `group_by: ["day", "intent"]` and `session_count`, `success_count`, `failure_count`, filtered by the agent. Split the day buckets into the same two windows and compare per intent. Intents that appear or disappear between the windows are as important as rate changes, but only call an intent new or gone when both windows have enough sessions for its absence to mean something.
+4. Find what moved: `aggregate_sessions` for the same covering range with `group_by: ["day", "intent"]` and `session_count`, `success_count`, `failure_count`, filtered by the MCP server. Split the day buckets into the same two windows and compare per intent. Intents that appear or disappear between the windows are as important as rate changes, but only call an intent new or gone when both windows have enough sessions for its absence to mean something.
 5. `list_signals` for the covering range. Signals that fired only after the boundary are candidate regressions; `get_signal` for evidence and affected sessions.
 6. Evidence: `list_sessions` filtered by `agent_name`, `from` the boundary, and `outcome: "unsuccessful"` or `user_feedback: "negative"`. Open at most three with `get_session`, and only the turn the analysis points at with `get_turn`. Then check one comparable before-window session for the same intent, so the difference is attributable to the release and not to the intent.
-7. Rule out confounders before concluding: a traffic mix shift (different intents or users after the boundary), an ingestion gap on either side, a concurrent change to another agent, and the analysis lag. Pinned notes and `list_agent_attributes` help with the first two.
+7. Rule out confounders before concluding: a traffic mix shift (different intents or users after the boundary), an ingestion gap on either side, a concurrent change to another MCP server, and the analysis lag. Pinned notes and `list_agent_attributes` help with the first two.
 8. If the app's release receipt is available, reconcile with it: it reports claim consistency, the delta versus the previous release, the production window, the prompt diff, sample sessions, and related signals. Those are fractions between 0 and 1. Report disagreements between your comparison and the receipt rather than picking one.
 9. If the regression or improvement is confirmed on more than one session and the numbers clear the sample floor, `save_note` with the finding, the boundary, the metrics before and after, and the intents involved. No personal data.
 10. `report_outcome`.
@@ -36,7 +45,7 @@
 ## Output shape
 
 ```
-Agent, release boundary, windows compared (days before / after), sessions on each side
+MCP server, release boundary, windows compared (days before / after), sessions on each side
 Verdict: improved / regressed / unchanged / too early, with the reason in one line
 Outcome metrics: before vs after table, with unanalysed share and sample floor notes
 Intents that moved: new, gone, or shifted, with counts
Full technical diff · 3 changed fields

changed /description

BEFORE
"Check whether a release of an agent changed its outcomes in Flowlines - compare sessions, success rates, intents, cost, and signals before and after a deploy over the Flowlines MCP server. Use when the user asks whether a deploy, prompt change, or new version regressed or improved anything, or wants a go/no-go after shipping."
AFTER
"Check whether an MCP server release changed session outcomes in Flowlines - compare sessions, success rates, intents, cost, and signals before and after a deploy over the Flowlines MCP server. Use when the user asks whether a deploy, prompt change, or new version regressed or improved anything, or wants a go/no-go after shipping. Do not use for a general review of the namespace (flowlines-weekly-review), one failing session (flowlines-investigate-session), or missing data (flowlines-doctor)."

changed /included_files

BEFORE
[
  {
    "relative_path": "agents/openai.yaml",
    "size_in_bytes": 227
  }
]
AFTER
[
  {
    "relative_path": "agents/openai.yaml",
    "size_in_bytes": 234
  }
]

changed /skill_md_contents

BEFORE
"---\nname: flowlines-release-check\ndescription: Check whether a release of an agent changed its outcomes in Flowlines - compare sessions, success rates, intents, cost, and signals before and after a deploy over the Flowlines MCP server. Use when the user asks whether a deploy, prompt change, or new version regressed or improved anything, or wants a go/no-go after shipping.\n---\n\n# Flowlines release check\n\nAnswer \"did the last release change anything?\" with numbers that have the right denominators, evidence from real sessions, and an honest statement of what cannot be known yet.\n\n## Conventions for every Flowlines tool call\n\n- Every tool takes `reason` and `user_intent`. Keep `user_intent` identical across the conversation, for example \"Check whether the 2026-09-01 release of the support agent regressed outcomes\".\n- Start with `get_workspace` once, then `get_context` for the namespace. Read pinned notes: a known evaluator artifact or ingestion gap changes how a comparison reads.\n- Quote the minimum from sessions and mask identifiers. Prefer aggregates.\n- End with `report_outcome` as the last tool call.\n\n## Inputs\n\n1. The agent. `list_agents` shows the names Flowlines observes; use the exact name in filters.\n2. The release boundary as an ISO 8601 timestamp. Take it from the user, the deploy log, or the release list in the Flowlines app under Versions. Flowlines records a release either from a reported agent version or from a detected prompt change; the app's release receipt shows which.\n3. The comparison window. Default to the same number of days on each side of the boundary, at least 3 and at most 14, so both sides have comparable traffic. Say when the after-window is still short.\n\n## Steps\n\n1. `get_changes_since` with `since` set to the release boundary. This gives the after-side activity, outcomes, signals, and pinned notes in one call.\n2. Build the two windows from day buckets. `aggregate_sessions` only accepts trailing ranges that end now (`24h`, `7d`, `30d`, `90d`, `all`), so any range you pick contains post-release activity. Query the smallest range that covers both windows with `group_by: [\"day\"]` and metrics `session_count`, `user_count`, `success_count`, `failure_count`, `total_cost_usd`, `unanalyzed_count`, filtered by `agent_name`. Assign each day bucket to the before or after window yourself. The deployment day is mixed: exclude it from both windows unless the boundary falls at the start of the day, and say which choice you made. Day buckets cannot represent a boundary inside a day exactly; say so, and if that precision matters use `list_sessions` with `from` and `to` around the boundary for counts on that day only.\n3. Compute rates from the summed counts, never by averaging per-day or per-group rates: success rate for a window is the sum of `success_count` divided by the sum of `success_count` and `failure_count` across its days. A status-grouped query is not a shortcut, because each status group has a rate of 0 or 100 percent by construction. `get_metric_definition` for `success_rate` and any other rate you report, and apply the sample floor to the window's combined denominator; below it, report counts and say the rate is not yet meaningful. Sessions in the after-window are still being analysed, so a high `unanalyzed_count` makes the after-side rate provisional.\n4. Find what moved: `aggregate_sessions` for the same covering range with `group_by: [\"day\", \"intent\"]` and `session_count`, `success_count`, `failure_count`, filtered by the agent. Split the day buckets into the same two windows and compare per intent. Intents that appear or disappear between the windows are as important as rate changes, but only call an intent new or gone when both windows have enough sessions for its absence to mean something.\n5. `list_signals` for the covering range. Signals that fired only after the boundary are candidate regressions; `get_signal` for evidence and affected sessions.\n6. Evidence: `list_sessions` filtered by `agent_name`, `from` the boundary, and `outcome: \"unsuccessful\"` or `user_feedback: \"negative\"`. Open at most three with `get_session`, and only the turn the analysis points at with `get_turn`. Then check one comparable before-window session for the same intent, so the difference is attributable to the release and not to the intent.\n7. Rule out confounders before concluding: a traffic mix shift (different intents or users after the boundary), an ingestion gap on either side, a concurrent change to another agent, and the analysis lag. Pinned notes and `list_agent_attributes` help with the first two.\n8. If the app's release receipt is available, reconcile with it: it reports claim consistency, the delta versus the previous release, the production window, the prompt diff, sample sessions, and related signals. Those are fractions between 0 and 1. Report disagreements between your comparison and the receipt rather than picking one.\n9. If the regression or improvement is confirmed on more than one session and the numbers clear the sample floor, `save_note` with the finding, the boundary, the metrics before and after, and the intents involved. No personal data.\n10. `report_outcome`.\n\n## Output shape\n\n```\nAgent, release boundary, windows compared (days before / after), sessions on each side\nVerdict: improved / regressed / unchanged / too early, with the reason in one line\nOutcome metrics: before vs after table, with unanalysed share and sample floor notes\nIntents that moved: new, gone, or shifted, with counts\nSignals since the release: severity, evidence, affected sessions\nEvidence sessions: ids and the turn each one points at (masked, minimal quotes)\nConfounders considered and how they were ruled out\nRecommendation: keep, watch, or roll back, and what to re-check tomorrow\nOpen questions (also sent as unmet_needs)\n```\n\n## Do not\n\n- Do not compare a 12-hour after-window with a 7-day before-window without saying the after-side is provisional.\n- Do not report a rate below its sample floor as a change.\n- Do not attribute a change to the release when the intent mix moved at the same time.\n- Do not paste transcripts; cite session ids and turn indexes.\n"
AFTER
"---\nname: flowlines-release-check\ndescription: Check whether an MCP server release changed session outcomes in Flowlines - compare sessions, success rates, intents, cost, and signals before and after a deploy over the Flowlines MCP server. Use when the user asks whether a deploy, prompt change, or new version regressed or improved anything, or wants a go/no-go after shipping. Do not use for a general review of the namespace (flowlines-weekly-review), one failing session (flowlines-investigate-session), or missing data (flowlines-doctor).\n---\n\n# Flowlines release check\n\nAnswer \"did the last release change anything?\" with numbers that have the right denominators, evidence from real sessions, and an honest statement of what cannot be known yet.\n\n## Tool discipline\n\n- Answer from the Flowlines MCP server first. It holds the data this skill works on, and every step below is written for its tools.\n- Use the Flowlines app, a browser, or web search only when the server cannot provide something the question needs, or when the user asks for it. Say that you are doing so and why. Never use them for data the server exposes, and never as a first move.\n- When part of the question stays unanswered, say so in the answer and list it in `unmet_needs` of `report_outcome`, with a pointer to where the user can look.\n- Match the effort to the question. For a plain question, make the minimum calls (`get_workspace`, `get_context`, then the one or two tools that answer it), answer, and `report_outcome`. Run the full procedure below only when the user asks for a release check or a go/no-go, and skip `save_note` and evidence sessions unless the procedure runs in full or the user asks for them.\n- If authentication is required, or a generic MCP error (such as `-32603`) repeats on one read-only check, use `flowlines-doctor` when available for connection recovery before further data calls. Client diagnostics and native sign-in are allowed for this repair. After verification, resume the original request with the same namespace, range, and `user_intent`.\n- If `flowlines-doctor` is unavailable, use only the failing client's connection status and native reconnect action. Reconnect once only when that client reports an authentication problem; leave browser consent to the user, then verify with one read-only call. If the action is unavailable, give the user the reconnect step in their client and wait for completion. For an unexplained generic error or failed verification, stop data calls, give the user the error and a pointer to Flowlines support. Do not access Flowlines infrastructure or present unavailable data as empty.\n\n## Conventions for every Flowlines tool call\n\n- Every tool takes `reason` and `user_intent`. Keep `user_intent` identical across the conversation, for example \"Check whether the 2026-09-01 release of the support MCP server regressed session outcomes\".\n- Start with `get_workspace` once, then `get_context` for the namespace. Read pinned notes: a known evaluator artifact or ingestion gap changes how a comparison reads.\n- Quote the minimum from sessions and mask identifiers. Prefer aggregates.\n- End with `report_outcome` as the last tool call.\n\n## Inputs\n\n1. The MCP server. `list_agents` shows the service names Flowlines observes; use the exact name in `agent_name` filters.\n2. The release boundary as an ISO 8601 timestamp. Take it from the user or the deploy log. If neither gives it, the release list in the Flowlines app under Versions has it and the MCP server does not; read it there or ask the user. Flowlines records a release either from a reported version or from a detected prompt change; the app's release receipt shows which.\n3. The comparison window. Default to the same number of days on each side of the boundary, at least 3 and at most 14, so both sides have comparable traffic. Say when the after-window is still short.\n\n## Steps\n\n1. `get_changes_since` with `since` set to the release boundary. This gives the after-side activity, outcomes, signals, and pinned notes in one call.\n2. Build the two windows from day buckets. `aggregate_sessions` only accepts trailing ranges that end now (`24h`, `7d`, `30d`, `90d`, `all`), so any range you pick contains post-release activity. Query the smallest range that covers both windows with `group_by: [\"day\"]` and metrics `session_count`, `user_count`, `success_count`, `failure_count`, `total_cost_usd`, `unanalyzed_count`, filtered by `agent_name`. Assign each day bucket to the before or after window yourself. The deployment day is mixed: exclude it from both windows unless the boundary falls at the start of the day, and say which choice you made. Day buckets cannot represent a boundary inside a day exactly; say so, and if that precision matters use `list_sessions` with `from` and `to` around the boundary for counts on that day only.\n3. Compute rates from the summed counts, never by averaging per-day or per-group rates: success rate for a window is the sum of `success_count` divided by the sum of `success_count` and `failure_count` across its days. A status-grouped query is not a shortcut, because each status group has a rate of 0 or 100 percent by construction. `get_metric_definition` for `success_rate` and any other rate you report, and apply the sample floor to the window's combined denominator; below it, report counts and say the rate is not yet meaningful. Sessions in the after-window are still being analysed, so a high `unanalyzed_count` makes the after-side rate provisional.\n4. Find what moved: `aggregate_sessions` for the same covering range with `group_by: [\"day\", \"intent\"]` and `session_count`, `success_count`, `failure_count`, filtered by the MCP server. Split the day buckets into the same two windows and compare per intent. Intents that appear or disappear between the windows are as important as rate changes, but only call an intent new or gone when both windows have enough sessions for its absence to mean something.\n5. `list_signals` for the covering range. Signals that fired only after the boundary are candidate regressions; `get_signal` for evidence and affected sessions.\n6. Evidence: `list_sessions` filtered by `agent_name`, `from` the boundary, and `outcome: \"unsuccessful\"` or `user_feedback: \"negative\"`. Open at most three with `get_session`, and only the turn the analysis points at with `get_turn`. Then check one comparable before-window session for the same intent, so the difference is attributable to the release and not to the intent.\n7. Rule out confounders before concluding: a traffic mix shift (different intents or users after the boundary), an ingestion gap on either side, a concurrent change to another MCP server, and the analysis lag. Pinned notes and `list_agent_attributes` help with the first two.\n8. If the app's release receipt is available, reconcile with it: it reports claim consistency, the delta versus the previous release, the production window, the prompt diff, sample sessions, and related signals. Those are fractions between 0 and 1. Report disagreements between your comparison and the receipt rather than picking one.\n9. If the regression or improvement is confirmed on more than one session and the numbers clear the sample floor, `save_note` with the finding, the boundary, the metrics before and after, and the intents involved. No personal data.\n10. `report_outcome`.\n\n## Output shape\n\n```\nMCP server, release boundary, windows compared (days before / after), sessions on each side\nVerdict: improved / regressed / unchanged / too early, with the reason in one line\nOutcome metrics: before vs after table, with unanalysed share and sample floor notes\nIntents that moved: new, gone, or shifted, with counts\nSignals since the release: severity, evidence, affected sessions\nEvidence sessions: ids and the turn each one points at (masked, minimal quotes)\nConfounders considered and how they were ruled out\nRecommendation: keep, watch, or roll back, and what to re-check tomorrow\nOpen questions (also sent as unmet_needs)\n```\n\n## Do not\n\n- Do not compare a 12-hour after-window with a 7-day before-window without saying the after-side is provisional.\n- Do not report a rate below its sample floor as a change.\n- Do not attribute a change to the release when the intent mix moved at the same time.\n- Do not paste transcripts; cite session ids and turn indexes.\n"
Full snapshot data
{
  "description": "Check whether an MCP server release changed session outcomes in Flowlines - compare sessions, success rates, intents, cost, and signals before and after a deploy over the Flowlines MCP server. Use when the user asks whether a deploy, prompt change, or new version regressed or improved anything, or wants a go/no-go after shipping. Do not use for a general review of the namespace (flowlines-weekly-review), one failing session (flowlines-investigate-session), or missing data (flowlines-doctor).",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 234
    }
  ],
  "name": "flowlines-release-check",
  "skill_md_contents": "---\nname: flowlines-release-check\ndescription: Check whether an MCP server release changed session outcomes in Flowlines - compare sessions, success rates, intents, cost, and signals before and after a deploy over the Flowlines MCP server. Use when the user asks whether a deploy, prompt change, or new version regressed or improved anything, or wants a go/no-go after shipping. Do not use for a general review of the namespace (flowlines-weekly-review), one failing session (flowlines-investigate-session), or missing data (flowlines-doctor).\n---\n\n# Flowlines release check\n\nAnswer \"did the last release change anything?\" with numbers that have the right denominators, evidence from real sessions, and an honest statement of what cannot be known yet.\n\n## Tool discipline\n\n- Answer from the Flowlines MCP server first. It holds the data this skill works on, and every step below is written for its tools.\n- Use the Flowlines app, a browser, or web search only when the server cannot provide something the question needs, or when the user asks for it. Say that you are doing so and why. Never use them for data the server exposes, and never as a first move.\n- When part of the question stays unanswered, say so in the answer and list it in `unmet_needs` of `report_outcome`, with a pointer to where the user can look.\n- Match the effort to the question. For a plain question, make the minimum calls (`get_workspace`, `get_context`, then the one or two tools that answer it), answer, and `report_outcome`. Run the full procedure below only when the user asks for a release check or a go/no-go, and skip `save_note` and evidence sessions unless the procedure runs in full or the user asks for them.\n- If authentication is required, or a generic MCP error (such as `-32603`) repeats on one read-only check, use `flowlines-doctor` when available for connection recovery before further data calls. Client diagnostics and native sign-in are allowed for this repair. After verification, resume the original request with the same namespace, range, and `user_intent`.\n- If `flowlines-doctor` is unavailable, use only the failing client's connection status and native reconnect action. Reconnect once only when that client reports an authentication problem; leave browser consent to the user, then verify with one read-only call. If the action is unavailable, give the user the reconnect step in their client and wait for completion. For an unexplained generic error or failed verification, stop data calls, give the user the error and a pointer to Flowlines support. Do not access Flowlines infrastructure or present unavailable data as empty.\n\n## Conventions for every Flowlines tool call\n\n- Every tool takes `reason` and `user_intent`. Keep `user_intent` identical across the conversation, for example \"Check whether the 2026-09-01 release of the support MCP server regressed session outcomes\".\n- Start with `get_workspace` once, then `get_context` for the namespace. Read pinned notes: a known evaluator artifact or ingestion gap changes how a comparison reads.\n- Quote the minimum from sessions and mask identifiers. Prefer aggregates.\n- End with `report_outcome` as the last tool call.\n\n## Inputs\n\n1. The MCP server. `list_agents` shows the service names Flowlines observes; use the exact name in `agent_name` filters.\n2. The release boundary as an ISO 8601 timestamp. Take it from the user or the deploy log. If neither gives it, the release list in the Flowlines app under Versions has it and the MCP server does not; read it there or ask the user. Flowlines records a release either from a reported version or from a detected prompt change; the app's release receipt shows which.\n3. The comparison window. Default to the same number of days on each side of the boundary, at least 3 and at most 14, so both sides have comparable traffic. Say when the after-window is still short.\n\n## Steps\n\n1. `get_changes_since` with `since` set to the release boundary. This gives the after-side activity, outcomes, signals, and pinned notes in one call.\n2. Build the two windows from day buckets. `aggregate_sessions` only accepts trailing ranges that end now (`24h`, `7d`, `30d`, `90d`, `all`), so any range you pick contains post-release activity. Query the smallest range that covers both windows with `group_by: [\"day\"]` and metrics `session_count`, `user_count`, `success_count`, `failure_count`, `total_cost_usd`, `unanalyzed_count`, filtered by `agent_name`. Assign each day bucket to the before or after window yourself. The deployment day is mixed: exclude it from both windows unless the boundary falls at the start of the day, and say which choice you made. Day buckets cannot represent a boundary inside a day exactly; say so, and if that precision matters use `list_sessions` with `from` and `to` around the boundary for counts on that day only.\n3. Compute rates from the summed counts, never by averaging per-day or per-group rates: success rate for a window is the sum of `success_count` divided by the sum of `success_count` and `failure_count` across its days. A status-grouped query is not a shortcut, because each status group has a rate of 0 or 100 percent by construction. `get_metric_definition` for `success_rate` and any other rate you report, and apply the sample floor to the window's combined denominator; below it, report counts and say the rate is not yet meaningful. Sessions in the after-window are still being analysed, so a high `unanalyzed_count` makes the after-side rate provisional.\n4. Find what moved: `aggregate_sessions` for the same covering range with `group_by: [\"day\", \"intent\"]` and `session_count`, `success_count`, `failure_count`, filtered by the MCP server. Split the day buckets into the same two windows and compare per intent. Intents that appear or disappear between the windows are as important as rate changes, but only call an intent new or gone when both windows have enough sessions for its absence to mean something.\n5. `list_signals` for the covering range. Signals that fired only after the boundary are candidate regressions; `get_signal` for evidence and affected sessions.\n6. Evidence: `list_sessions` filtered by `agent_name`, `from` the boundary, and `outcome: \"unsuccessful\"` or `user_feedback: \"negative\"`. Open at most three with `get_session`, and only the turn the analysis points at with `get_turn`. Then check one comparable before-window session for the same intent, so the difference is attributable to the release and not to the intent.\n7. Rule out confounders before concluding: a traffic mix shift (different intents or users after the boundary), an ingestion gap on either side, a concurrent change to another MCP server, and the analysis lag. Pinned notes and `list_agent_attributes` help with the first two.\n8. If the app's release receipt is available, reconcile with it: it reports claim consistency, the delta versus the previous release, the production window, the prompt diff, sample sessions, and related signals. Those are fractions between 0 and 1. Report disagreements between your comparison and the receipt rather than picking one.\n9. If the regression or improvement is confirmed on more than one session and the numbers clear the sample floor, `save_note` with the finding, the boundary, the metrics before and after, and the intents involved. No personal data.\n10. `report_outcome`.\n\n## Output shape\n\n```\nMCP server, release boundary, windows compared (days before / after), sessions on each side\nVerdict: improved / regressed / unchanged / too early, with the reason in one line\nOutcome metrics: before vs after table, with unanalysed share and sample floor notes\nIntents that moved: new, gone, or shifted, with counts\nSignals since the release: severity, evidence, affected sessions\nEvidence sessions: ids and the turn each one points at (masked, minimal quotes)\nConfounders considered and how they were ruled out\nRecommendation: keep, watch, or roll back, and what to re-check tomorrow\nOpen questions (also sent as unmet_needs)\n```\n\n## Do not\n\n- Do not compare a 12-hour after-window with a 7-day before-window without saying the after-side is provisional.\n- Do not report a rate below its sample floor as a change.\n- Do not attribute a change to the release when the intent mix moved at the same time.\n- Do not paste transcripts; cite session ids and turn indexes.\n"
}

SHA-256 of public snapshot: 508fbf14bbde7b6b3b035178b840a3edb23e40f3217aad1a8f3308cc9d8cdb75