Support/Builder Guide/Rating GoClaw and improving results

Builder Guide

Rating GoClaw and improving results

Every action can be rated, every suggestion explains itself — so poor results can be diagnosed, not just endured.

Explicit signal
1–5 rating + comment on any executed action
Implicit signal
Every suggestion's fate is recorded
Diagnosis
The AI's reasoning is stored, not discarded

An assistant you can't grade is an assistant you can't improve. GoClaw is built the other way around: every piece of work it does generates signals, every suggestion keeps a record of why it was made, and the path from “that was a bad draft” to “here's exactly what to change” is a read, not a guess.

The signals, explicit and implicit

Explicit ratings. After an action executes, the user can rate it one to five, mark whether it was helpful, and leave a comment. Ratings attach to the specific execution — not to the assistant in general — so a 2-star is always a 2-star on something inspectable.

Implicit responses. Richer still: every suggestion the assistant makes records its fate — accepted, dismissed, ignored, or modified and accepted — along with where it ranked in the list and how confident the AI was at the time. Nobody has to remember to rate anything for this signal to accumulate; using the assistant normally produces it.

Rejection reasons. When an approver rejects a queued action they can say why, and the reason is stored on the action and in its event trail. A week of rejection reasons is a tuning brief written by your own users.

ResponseWhat it tells you
Accepted as-isThe draft was right. The baseline you're protecting.
Modified, then acceptedThe most valuable signal there is: the idea was right, the execution needed polish. Read the edits — they're your users showing you the target.
DismissedWrong action for the moment. If one action type is dismissed persistently, its triggering conditions are too broad.
IgnoredNot even engaged with. Chronic ignoring means suggestions are surfacing at the wrong time or place, not just with the wrong content.

Diagnosing a poor rating

What makes diagnosis possible is that the assistant's homework is retained. Each suggestion stores a snapshot of the data it saw at that moment and its reasoning — the factors it weighed, how heavily, and the alternative actions it considered with their scores. Each execution stores a step-by-step trail: every step's input, output, duration, and any error. So a bad outcome decomposes into one of three findings:

FindingYou'll see it inThe fix lives in
It saw the wrong data — the snapshot is missing or stale relative to realityThe context snapshot vs. the actual record at that timeData quality and what context the action is fed — not the AI's behavior
It reasoned poorly — right data, wrong weighting or wrong alternative chosenThe reasoning's factors and the scores on alternatives it passed overThe behavior configuration: prompts, factor emphasis, and the conditions that trigger each action type
It executed badly — right decision, a step failed or produced a poor artifactThe execution steps: which one erred, how long it took, what it emittedThe specific step — a template, a connected channel, a timeout
Tip

Start every diagnosis with the reasoning, not the output. “What did it think it was doing, and was that reasonable given what it saw?” separates a data problem from a judgment problem in about thirty seconds — and they have completely different fixes.

Closing the loop

Diagnosis without a safe way to ship the fix just moves the frustration. The improvement loop here is deliberately gated:

  1. Read the signals — ratings, response patterns, and rejection reasons, sliced by action type. One action type usually accounts for most of the pain.
  2. Diagnose with the stored evidence — snapshot, reasoning, steps, as above.
  3. Adjust the behavior configuration — the prompt, the triggering conditions, the context provided, or simply disabling an action type that isn't earning its place.
  4. Prove it before it ships — run the candidate configuration through a Harness Pack that includes scenarios built from the failures you just diagnosed. A fix that passes the scenarios that used to fail is a fix; anything else is a hope.
  5. Promote and watch the same metrics — the ratings and response rates that flagged the problem are the same ones that confirm the cure.
Note

Feedback also works passively: user responses feed suggestion ranking over time, so consistently dismissed suggestions sink and consistently accepted ones surface earlier — the feed self-corrects between your deliberate tuning passes.

The numbers worth watching

  • Acceptance rate by action type — the headline. A type below your comfort line is a tuning candidate; a type near zero should be switched off until fixed.
  • Modified-and-accepted share — high is actually encouraging early on (right ideas, improvable drafts); the goal is converting it into accepted-as-is by learning from the edits.
  • Rating trend across a configuration change — the before/after that tells you whether a tuning pass worked in production, not just in the Harness Pack.
  • Ignore rate — the placement-and-timing metric. Content fixes won't move it; where and when suggestions appear will.

Capability review: 2026-09-14. For exact current technical availability, use the generated API Map and first-class module inventory.