Product

Four dials. Two interfaces. One artifact.

Taste gives companies four dials — task, codebase, models, budget — and gives candidates exactly two interfaces: an OpenAI- and Anthropic-compatible model gateway and a built-in git remote. Everything the platform knows comes from those two channels.

The four dials

Everything a company configures per assessment.

01

Task

A real slice of work plus a definition of done. From the template library or your own repo and acceptance criteria.

02

Codebase

A repo snapshot cloned into every session. Scrubbed and scoped, sized for a single session of work.

03

Models

An allowlist of models behind simple aliases — eco, standard, premium — served by your configured model providers.

04

Budget

A token budget and a time window. Metered exactly, enforced in real time, surfaced to the candidate as a live meter.

Two interfaces

The candidate's side is their own machine.

No sandbox to fight, no browser extension, no screen recording. The candidate's whole footprint is model traffic and git pushes — which is exactly what real work produces.

The model gateway

/v1/chat/completions and /v1/messages, streamed, with tool use. Any agent works with a one-time session key. Anthropic requests are converted for OpenAI-format backends and converted back — transparently. Every request is metered to the exact token and written into the session transcript.

# Claude Code, pointed at a Taste session
ANTHROPIC_BASE_URL=https://tasted.dev/s/{session}/v1
ANTHROPIC_AUTH_TOKEN=sk-taste-…
ANTHROPIC_MODEL=standard

The git remote

A push-only, per-session remote. History is immutable — force-pushes are rejected — and every pushed commit triggers a CI run on the platform. The commit stream is the session timeline; nothing a candidate ships can bypass it.

# From the candidate's machine
git clone https://tasted.dev/git/{session_id}
# …work, commit, push — like any normal day
git push origin main
One artifact

The session record.

The commit timeline merged with the agent transcript and every CI result — immutable, evidence-linked, and replayable. This is what reviewers open, and what every score points back into.

session record · 7f3a · merged timeline
13:58 model plan: read checkout path, list 3 hypotheses 41k
14:02 push a3f9c12 repro: failing test for checkout race
14:19 model abandons retry theory, traces reservation lock 96k
14:31 push b7d21e4 fix: serialize inventory reservation
14:44 push c90aa01 test: regression for 8 PM ET burst
14:45 score outcome 4/5 · process 5/5 · quality 4/5 IC5
Every line is a link: the commit's diff, the CI log, or the exact transcript exchange.

Commit time-lapse

Watch the repo evolve at N× speed. Pause at any commit: its diff, its CI result, and what the agent was doing at that moment.

The red-to-green journey

CI history shows how they handled failure — and how long they were willing to live in red.

Budget-per-commit

Tokens spent per unit of shipped work. Where the budget went, and what it bought.

Transcript vs. commits

Tool activity from the transcript compared automatically against what was committed — drift between the two is a signal in itself.

Under the hood

Engineered like the infrastructure it is.

01

Protocol conversion, both directions

Anthropic-format requests are converted for OpenAI-format backends and back — tool calls, streaming, and usage accounting included. One session key speaks both dialects.

02

Exact metering, enforced live

Token usage is counted per request — streamed or not — and enforced against the budget in real time. GET /v1/budget tells the candidate exactly where they stand.

03

Secure by default

Ephemeral per-session credentials, encrypted provider keys, immutable git history, full audit trail. Built in Rust — no unsafe, pedantic-lint clean.

“The session replay shows the plan, the tradeoffs, the debugging, the recovery from dead ends. The PR shows the code. The budget curve shows the judgment. Together they give you what a two-hour conversation never will: what this person is like at a keyboard, solving your problem, under real constraints.” — The Taste team

Run a sample task against your own repo.

Set the four dials, send one invite, and open your first session record — in under a day.