Skip to content
Midbar
ProductThesisResearch
Talk to us
ProductThesisResearchTalk to us

Notes

A few longer reads

Start with the thesis if you want the full argument. These are shorter cuts into data, eval, and deploy.

Data

Sessions beat docs as training data

A wiki says what should happen. A session shows what someone did when the ticket was incomplete.

Read note →

Evaluation

Grade the tool path, not only the answer

Correct finals can hide bad process. For operational work, the path is part of the product.

Read note →

Systems

From laptop sessions to a model you can ship

Capture, clean, train, measure, deploy. The artifact is weights, not a forever API hop.

Read note →
Midbar

M_workload = distill(τ_team)

Small models trained on how your team already works.

Remote-first · Contact [email protected]

Product

How it worksDeploymentEvaluation

Research

ThesisNotesOpen source

Company

AboutContactPrivacy
© 2026 Midbar AI
PrivacyTerms