Skip to content
SENTRY-PROTOCOL COMPATIBLE

Error tracking that ends in a pull request.

Parsemend speaks the Sentry protocol, so the SDK you already installed keeps working. Then an agent reads the stack trace, names the root cause, and opens a draft pull request against the line that threw.

1 line to migrate4 modes to run the agent0 markup on tokens

incidentproduction · first seen 6 min ago×47 events

TypeError: Cannot read properties of undefined (reading 'id')

src/auth/session.ts:142
draft pr #214fix-run #a41c92
scan   fixability 0.92 > threshold 0.80cause  auth retry races the session refreshrepro  POST /api/session -> 401 -> stale readplan   guard session.user before read (+4 -1)
src/auth/session.ts:142
unchanged line: const session = await refreshSession(token)removed line: return session.user.idadded line: if (!session?.user) {added line:   throw new AuthRetryError('session invalidated')added line: }added line: return session.user.id
outcomegithub.com/acme/api
Draft PR #214 opened — awaiting your review
Replay of a fix run. The agent drafts; you review and merge.
the fix run

Five steps, and you can stop it at any of them.

Each step is a checkpoint with a confidence score attached. A run that dies at step three resumes at step three. A run that is not confident enough pauses and waits for you.

  1. 01scan

    Scan

    The issue is scored for fixability. Runs start only above the project's threshold.

  2. 02root cause

    Root cause

    The agent reads the context bundle and states, in one sentence, what is actually wrong.

  3. 03plan

    Plan

    A change plan, before any code. You can edit it, or reject it, before a line is written.

  4. 04patch

    Patch

    The plan becomes a diff. Confidence below threshold pauses the run instead of guessing.

  5. 05draft PR

    Draft PR

    A draft pull request, with the root cause in the description. You review and merge.

run it your way

Four ways to run the agent. Three of them never show us your code.

The fix run is the product. Where it executes, whose model it calls and who pays for the tokens are yours to choose.

the tracker

The whole tracker, not a demo of one.

The agent is the reason to pay. It is not an excuse for a thin error tracker underneath it.

  • Sentry SDK compatible

    shipped

    Keep the SDK you already installed. Envelope and legacy store endpoints, all three DSN auth forms, unknown item types tolerated rather than rejected.

  • Grouping that survives refactors

    shipped

    Custom fingerprint, then in-app frame signatures with recursion collapsed, then exception type and value, then a parameterized message. Many hashes fold into one issue.

  • Regression detection

    shipped

    A resolved issue that sees a new event flips to regressed. No cron, no sweep — it happens on the write path.

  • Breadcrumbs and context

    shipped

    The last N things that happened before the throw, normalized and stored with the event rather than sampled away.

  • Tags, environments, releases

    shipped

    Indexed as a key/value table, not scanned out of JSON at query time. Filter issues by environment or release without a full-text search.

  • Rate limits and quotas

    shipped

    Per-key fixed-window limiting that answers with 429, Retry-After and X-Sentry-Rate-Limits, so your SDK backs off the way it already knows how.

  • Retention by partition drop

    shipped

    Events live in a range-partitioned table. Expiring a day is a DDL statement, not a mass delete that vacuums for an hour.

  • Source maps and alert rules

    planned

    Upload artifacts with debug IDs so minified frames resolve to your source. Route issues to email, Slack or a webhook on the conditions you set.

cost

Two bills, on purpose.

You pay Parsemend a flat fee for the framework: context bundles, the fix-run state machine, confidence gating, PR post-back. You pay your model provider for inference, directly, at their raw token prices. We never resell inference, so we never have a reason to send you a bigger model than the job needs.

framework fee

Parsemend

flat

A flat monthly fee. It does not move when your error volume spikes or when you switch models.

metered inference

Your model provider

raw

Whatever the run actually consumed, billed to your account by Anthropic, OpenAI, Google — or nobody, if you run Ollama.

In managed mode there is only one bill, because the tokens are ours. See the pricing breakdown.

evidence

How you will know whether it works.

Every fix run is scored against a benchmark suite of real, closed issues with known-good patches. The methodology, the suite and the pass rate are published — including the runs where the agent produced a patch that did not hold.

Results are published with the benchmark methodology rather than quoted as a headline figure. If a number here cannot be reproduced from the suite, it should not be here.

a note from the founder

There are no customer logos on this page, and no testimonials, because Parsemend has no customers yet. Putting fake ones here would be the first lie, and there is no good place to start.

What there is instead: the ingest pipeline is documented down to which Content-Encoding values it accepts, the fix-run state machine is described step by step, and the comparison tables cite Sentry's own pages with the date we read them. If something on this site is wrong, mail me and I will change it.

Vasil Cholakov, founder and engineer

Error tracking is free forever. The agent is why you'll pay.

No credit card for the free tier. Free signups never consume our model tokens.