A product manager for your AI agent.Analyze what worked, what to improve, and find out what to build next.
Agent
Intents7d30dAll
What the agent doesRunsSuccess
Generate a part drawing1,24095%
Check a tolerance stack76091%
Detect an interference29054%
Run a stress analysis48086%
Generate a CNC toolpath new90build next →
Flagged this week: 1 intent to fix, 1 to build next.
Works with
Auto-instruments
OpenAIAnthropic
Ships issues to
LinearGitHub
01 What you see
Three views of your traffic: the goals users bring, what your agent did on each run, and the requests it can't handle yet. This is the product layer, not a trace viewer. Every run carries an outcome you defined, so a row reads completed or failed at a step, not just the model replied.
Refund a charge96%
Track my order92%
Change my plan61%
Cancel subscription79%
verify_user · auth · 38ms
lookup_order · orders-db · 42ms
notify_user · email · 19ms
✓ success
Book a callbacknew118
Split a paymentnew64
Pause my accountnew41
Gift a subscriptionnew27
02 How it works
Add the SDK once. After that it's the same loop every week: see what's failing, fix the biggest one, build the request people keep making.
i.
Patch your client once. Every run is recorded: model, tokens, latency, and a success or failure verdict you define, not a model's guess.
ii.
Each run is labeled with the user's goal as a named business intent like refund_request. You declare it, or we infer it per run from the input.
iii.
Runs with the same goal are grouped. Failures and missing features sort by how often they happen.
iv.
You fix the top problem and build the top request.
v.
The numbers go up. Next week, you do it again.
03 It compounds
Each fix raises one intent's success rate. Over a month, that's the gap between an agent people put up with and one they trust.
Success rate, week by weekillustrative
W1fixed identity verification
W2fixed a refund edge case
W3shipped order tracking
W4shipped callback booking
04 Close the loop
Turn any failure or unmet request into a Linear or GitHub issue, pre-filled with the evidence, in one click.
failure · 61%
Change my plan
43% of failures: can't verify identity
→
LinearGitHub
Fix: Change my plan succeeding at 61%, can't verify identity
Impact160 failed runs/wk (~96 tickets)
Wherefails at verify_user (auth), no fallback
☐ success ≥ 85%☐ add OTP fallback
bugagentfrom-intencion
05 Install
Every call is captured: model, tokens, latency, and outcome. It works at the class level, so calls your framework makes on its own are caught too. TypeScript and Python.
agent.ts
import
{
Intencion
}
from "@intencion/sdk";
import Anthropic from "@anthropic-ai/sdk";
const ix = new Intencion(
{
apiKey
}
);
const anthropic = ix.instrumentAnthropic(new Anthropic());
// every call captured: model, tokens, latency, outcome.
tools.ts
await ix.run(
{
intent: "refund_request", input
}
, async (run) =>
{
const order = await run.tool("lookup_order", "orders-db", () => lookupOrder(id));
return await issueRefund(order); // returns → success
}
);
Start free in a minute. No call required, or try the live demo first.