How to QC an Agent
Who this is for: Anyone asked to check a new Agent before client use.
Goal: Use the Agent 10–20 times across real scenarios and log any issues (“snags”) on the QC Monday board.
1) Before you start (2 mins)
- Open Assist Direct Chat (or any Output chat) and tag the Agent.
- Jot down 3–4 real scenarios you actually handle (e.g., first outreach, discovery call, pricing objection, troubleshooting).
- Open the QC Monday board in another tab.
2) What “good” looks like
- Follows your instructions (tone, length, format, channel).
- Stays consistent with the persona or role you set; doesn’t drift.
- Gives realistic pushback/asks sensible questions; not generic.
- Handles constraints (e.g., “max 120 words”, “bullets only”).
- If asked to step out of character, gives clear, brief feedback, then returns to character when told.
3) Run your tests (target: 10–20 uses)
Keep each run short (1–3 minutes). Mix these:
A. Setup & persona
- Define role, industry, size, pain points, style, and authority level.
- Switch persona mid-session to check reset behaviour.
B. Scenarios & channels
- First cold email (100–150 words).
- LinkedIn DM (3 messages each).
- Discovery call (5–8 questions; time-pressed).
- Negotiation (pricing, scope, legal/compliance).
- “Bad brief” test: vague or missing info—does it ask clarifying questions?
C. Difficulty & format
- “Be more sceptical” / “warmer but cautious”.
- “Max 120 words” / “bullet points only” / “include 1 question”.
- Add a curveball (new stakeholder, legacy system, budget freeze).
D. Feedback toggle
- “Step out of character and critique my last two messages (clarity, value, CTA). Then return to character.”
Tip: Note pass/fail quickly. You’ll log one snag per issue you find.
4) Log snags on the QC Monday board
Use the standard columns:
- Name — short title of the issue
- Link to Output/Chat — paste the exact chat URL
- What task were you trying to do? — 1–2 lines of the scenario
- What happened? — actual behaviour (what you saw)
- What was the expectation? (What should have happened) — 1–2 lines
- Severity — Low / Medium / High / Critical
- Screenshots (Optional) — attach or link
- Status (For Wooshii use) — leave blank
Severity guide
- Critical: breaks core behaviour or blocks use.
- High: major inconsistency; frequent.
- Medium: intermittent quirks; workarounds exist.
- Low: polish (phrasing, minor formatting).
Example snag (Agent)
- Name: Breaks character without being asked
- Link to Output/Chat:
https://…/assist/direct/abc123
- What task were you trying to do? Pricing negotiation with a Procurement persona (formal, concise).
- What happened? After my third message, the Agent started coaching me (not in character).
- Expectation: Stay in persona until I explicitly ask to step out of character.
- Severity: Medium
- Screenshots: (attached)
5) Finishing up
- If you hit no snags, ping us via email and let us know you hit no snags and that QC is complete.
- Need help? Reply to the rollout email; we’ll jump on a quick walkthrough.