The record already exists
Claude Code, Codex, and Cursor keep local records of every session: prompts, tool calls, retries, and results. Quesma processes the files your agents already create.
How it works
From sessions to answers.
Your coding agents already write down everything they do. Quesma collects those records, removes what should never leave a laptop, and turns the rest into a picture your whole organization can use.
What Quesma reads
The evidence is already on the laptop.
Quesma reads what your tools write down anyway. Nothing about how your agents run has to change.
Open-source collector
The collector that reads those files runs in your environment. Your engineers and security team can inspect every line.
Agents stay as they are
No proxy, rerouting, or changed behavior. Quesma never sits between developers and their agents.
Open data layer
Sessions land in open, documented tables you can query with the engines you already run. The record stays yours if you stop using Quesma.
FROM USAGE TO EVIDENCE
Your bill shows tokens. Quesma shows the work.
Provider dashboards tell you how much your team used. They cannot tell you whether that usage fixed a bug, shipped a patch, or repeated the same failed approach for an hour.
- Repeated work
The same test and context run again without a code change.
YOUR TEAM CANStop costly retry loops. - Model mismatch
A high-cost model handles work that does not need its full capability.
YOUR TEAM CANRoute routine work to a lower-cost model. - Verified delivery
Tested changes are separated from long sessions that ship nothing.
YOUR TEAM CANScale the workflows that deliver.
PRIVATE BY ARCHITECTURE
Your sessions stay in your cloud.
Secrets, credentials, and sensitive values are removed on the developer machine, before anything is uploaded. The collector then writes directly to object storage your company controls.
YOUR DATA PLANE
- SOURCEAgent sessionsdeveloper environment
- LOCALCollection + redactionbefore upload
- OWNEDCustomer storageopen tables
- MEASUREQuesma analyticsnot in the upload path
MEASUREMENT≠INTERVENTION
People, not scores
We analyze the agents. We don't score the engineers.
Quesma shows patterns across teams, repositories, and kinds of work. It does not turn those patterns into a ranking of people. Reading an individual's sessions takes permission, granted per role and never assumed.
Leadership sees the structure of the work, never a productivity score with an engineer's name attached.
employee AI scoreemployee token rankingvibe coding compliancepersonal slop quota
Frequently Asked Questions
Asked before every rollout.
- Privacy
Is this a surveillance tool?
No, and the design shows it rather than promises it. Leadership and finance views are structural: teams, repositories, and kinds of work. There are no manager-facing leaderboards, and access to session content is explicit and role-based.
- Data custody
Does our code leave our infrastructure?
No. The open-source collector uploads directly to object storage your company owns, and sensitive values are removed on the developer’s machine before anything leaves it.
- Workflow
Do we have to change how our agents run?
No. Quesma reads the files your tools already produce. There is no proxy and no rerouting.
Next step
The record already exists. Start analyzing it.
Early access is opening soon for teams using Claude Code, Codex, or Cursor, ones where engineering and finance both need answers about agent spend.