Your AI agent failed.
Again.
The final answer is wrong, but the logs look fine:
tool call started
model call started
tool call completed
model call completed
fallback used
error: timeout
Which tool caused the timeout? Did the model answer before retrieval finished? Was the fallback expected? Did the agent call the same tool twice?
This is where console.log
stops feeling like debugging and starts feeling like archaeology.
I kept hitting this problem while building TypeScript AI agents. Once the flow moved beyond a single model call, the debugging loop became a system:
plan → retrieve → rank → generate → validate → maybe retry → maybe hand off
Flat logs lost the structure. Output only tests could miss a bad path that happened to produce a plausible answer. Model graded evals helped with semantic quality, but they were a poor fit for every deterministic CI rule. And raw traces were too risky to paste casually into issues or pull requests.
So I built agent-inspect.
AgentInspect is a local evidence debugger and trajectory-test toolkit for TypeScript AI agents.
It turns one local trace into three things: a readable execution tree, a deterministic regression gate, and a derived Evidence v2 bundle that you can review before sharing.
No account. No collector. No default upload. Metadata only by default.
one local JSONL trace
├─ Debug → view · report · explain
├─ Prevent → check · contract · CI
└─ Share → redact · bundle · verify
A support agent can return a plausible answer after doing almost everything wrong.
The healthy path might be:
plan-request
└─ retrieve_policy
└─ rank-results
└─ generate_answer
└─ policyShown: passed
The regression might be:
generate_answer <- answered before retrieval
retrieve_policy
retrieve_policy <- duplicate call
search_docs <- wrong tool, failed
policyShown: failed
An output only test may pass. A flat log may contain every event. Neither makes the wrong path obvious.
The final answer is only one fact about the run. Tool choice, ordering, repetition, completion, duration, token usage, and observed outcomes are facts too. Together, those facts form the agent's trajectory.
That trajectory should be inspectable. It should also be testable.
You can start with manual instrumentation:
import { inspectRun, observeOutcome, step } from "agent-inspect";
const answer = await inspectRun(
"support-agent",
async () => {
const policy = await step(
"retrieve_policy",
() => retrievePolicy(),
{
type: "tool",
metadata: { toolName: "retrieve_policy" },
},
);
const result = await step(
"generate_answer",
() => draftAnswer(policy),
{
type: "llm",
metadata: { model: "your-model" },
},
);
await observeOutcome("policyShown", {
expectation: "The answer cites a retrieved policy",
status: "passed",
method: "custom",
});
return result;
},
{ traceDir: ".agent-inspect" },
);
The wrapper records those boundaries as local JSONL while preserving the application's return value and errors. Raw prompts and model outputs are not required for the core workflow.
If your application already emits structured logs or uses AI SDK, OpenAI Agents JS, LangChain, or LangGraph you can use an adapter or reader instead of wrapping every step manually.
The shortest path uses a generated synthetic demo:
npm install agent-inspect
npx agent-inspect init --yes
node examples/agent-inspect-demo.mjs
npx agent-inspect list --dir .agent-inspect
init
writes a small config and demo into your project. The demo does not call a model or upload a trace.
Copy the run ID printed by list
, then use the same local artifact for the three jobs below.
npx agent-inspect view <run-id> --dir .agent-inspect --summary
npx agent-inspect report <run-id> --dir .agent-inspect
npx agent-inspect explain <run-id> --dir .agent-inspect
The tree restores the structure that flat logs lose: nested steps, tool and model calls, durations, safe metadata, errors, and observed outcomes. explain
summarizes local trace facts deterministically; its default path makes no provider call.
The useful question changes from:
Did the run fail?
to:
Where did the passing and failing trajectories first diverge?
That distinction matters when the visible answer looks fine but the agent skipped a required retrieval, safety, or validation step.
Some agent quality questions are subjective. Helpfulness, tone, and open ended answer quality can benefit from model graded evaluation.
But many regressions are structural:
retrieve_policy
called?search_docs
tool appear?Those checks do not need another model. They can be deterministic:
npx agent-inspect check <run-id> --dir .agent-inspect \
--preset trajectory \
--required-tool retrieve_policy \
--forbidden-tool search_docs \
--fail-on-observation failed
The preset and explicit shorthand rules are additive. A healthy run exits 0
; a trajectory-rule failure exits 1
.
For the committed regression fixture, the result is concrete:
Check status: fail
Summary: 2 failed, 0 warning(s), 0 error(s)
- outcome.status: Observed outcome count 1 matched [failed].
- tool.usage: Forbidden tool search_docs appeared.
Same trace. Same rules. Same verdict. No model judge and no provider call in the check path.
That makes it suitable for a normal CI step. If your test fixture writes a trace to a stable path:
- name: Run deterministic agent fixture
run: node run-agent-fixture.mjs
- name: Check agent trajectory
run: |
npx agent-inspect check .agent-inspect/ci-run.jsonl \
--preset trajectory \
--required-tool retrieve_policy \
--fail-on-observation failed \
--evidence-on fail
--evidence-on fail
writes local Evidence for triage when the check fails. It does not upload the artifact.
When CLI flags outgrow one command, the Beta TraceContract API expresses the same expectations in TypeScript:
import { openTraceFile } from "agent-inspect/readers";
import {
defineTraceContract,
evaluateTraceContractRead,
} from "agent-inspect/checks";
const read = await openTraceFile("./.agent-inspect/demo-regression.jsonl");
const contract = defineTraceContract({
run: { requireCompleted: true },
tools: {
required: ["retrieve_policy"],
forbidden: ["search_docs"],
},
observations: { failOn: ["failed"] },
});
const result = evaluateTraceContractRead(read, contract);
if (result.status !== "pass") process.exitCode = 1;
The principle is simple: use deterministic trace facts for structural CI rules, and reserve model grading for semantic quality.
A failing trace is often the best debugging artifact. It can also contain prompts, tool arguments, retrieved documents, customer identifiers, error messages, or secrets.
The collaboration strategy should not be “paste the raw trace into Slack.”
AgentInspect keeps the source trace read-only and creates a derived bundle:
npx agent-inspect verify-safe <run-id> --dir .agent-inspect
npx agent-inspect bundle <run-id> --dir .agent-inspect \
--profile share \
--out ./evidence
npx agent-inspect bundle verify ./evidence
The bundle can include:
evidence.html self-contained offline review surface
evidence.json versioned manifest and SHA-256 file hashes
trace.jsonl redacted derived trace
check-results.json deterministic findings
redaction-report.json detector summary without secret values
summary.md human-readable overview
bundle verify
checks the manifest, listed files, hashes, assessment, and provenance offline.
This is an integrity check. It is not a signature or a compliance certificate.
The wording matters: the artifact is share-checked, not “certified safe.” verify-safe
and redaction are best-effort controls. Review the generated HTML and safety results before attaching a bundle to a pull request, incident, or public issue.
The local evidence model is not tied to one agent framework.
| Your stack | Capture path |
|---|---|
| Custom TypeScript functions or classes | |
inspectRun , step , observe , or createInspector |
|
| Vercel AI SDK | @agent-inspect/ai-sdk |
| OpenAI Agents JS | @agent-inspect/openai-agents |
| LangChain or LangGraph | @agent-inspect/langchain |
| Existing structured logs | |
agent-inspect logs readers |
|
| OpenInference or OTLP JSON | local standards readers |
| Vitest or Jest | reporters plus experimental trace matchers |
The root package is enough for custom capture, the CLI, deterministic checks, and Evidence. Optional packages add only the integration you need.
The Preview MCP path exposes configured local evidence through bounded, read-only tools:
npx agent-inspect mcp configure --client cursor
The command is a dry run by default, so you can review the generated configuration before enabling it.
A connected coding assistant can then investigate the same TraceFacts used by the CLI: What failed first? Which required tool was missing? What changed between the passing and failing runs?
This is not replay, an auto fix engine, or a hidden upload path. It is optional read-only access to explicitly configured local evidence.
AgentInspect owns the laptop to pull request evidence loop:
capture locally
→ understand the path
→ fail CI on structural drift
→ derive reviewable evidence
It complements hosted observability and evaluation platforms. Use hosted tools when you need production dashboards, long term retention, fleet wide alerting, team wide trace search, hosted datasets, or prompt management.
Use AgentInspect when you need to inspect one TypeScript agent run immediately, enforce deterministic trajectory expectations in CI, compare a passing and failing local run, or hand off a redacted, hash-verifiable artifact.
The boundary is intentional. AgentInspect is not:
The current release is 6.17.2, requires Node.js 20 or newer, uses persisted schema 1.0
, and is MIT licensed. Legacy v0.1 and v0.2 traces remain readable.
npm install agent-inspect
npx agent-inspect init --yes
node examples/agent-inspect-demo.mjs
npx agent-inspect list --dir .agent-inspect
Then inspect, check, and derive Evidence from the run:
npx agent-inspect view <run-id> --dir .agent-inspect --summary
npx agent-inspect check <run-id> --dir .agent-inspect --preset trajectory
npx agent-inspect bundle <run-id> --dir .agent-inspect \
--profile share \
--out ./evidence
npx agent-inspect bundle verify ./evidence
One local trace should be able to tell you what the agent did, prove that the regression stays fixed, and give a teammate evidence they can review without making upload the price of admission.
AgentInspect is open source and MIT licensed. If this workflow is useful to you:
Most of all, leave a comment below.
How do you debug agent runs today?
Which trajectory rule would you put in CI first?
And if AgentInspect does not fit your workflow, tell me why that feedback is just as useful.