7 posts tagged with "x07"

Previously: How to Trust X07 Code Written by Coding Agents

The previous posts explained why X07 exists and how its trust model works. This one is the walkthrough: scaffold a service, add domain logic, wire up tests and contracts, and produce a certificate bundle that lets a reviewer approve the change without reading the whole source tree.

A coding agent can run every step below in a single session. That is the part that matters.

Series navigation: Previous: How X07 Was Designed for 100% Agentic Coding · Post 3 of 3

Most code written by coding agents should not be trusted on sight.

That is not because agents are useless. It is because normal languages and normal toolchains were built for human review, not for machine-checkable trust. So the default reaction is still, "I need to read the code." X07 changes that by changing what counts as evidence.

Two ideas from other engineering fields make this possible. Formal verification means using mathematical proof to show that code does exactly what its specification says — not "we ran some tests and they passed," but "we can prove this function never returns a negative number under any input." Code certification takes that further: it bundles proofs, test results, architecture checks, and runtime evidence into a structured package — a certificate — that a reviewer can inspect and approve without reading every line of source. Think of a building inspection report: you do not need to watch every nail go in if you trust the inspection process, the inspector's credentials, and the evidence they collected. The principle is not new. Clover showed that verification can act as a strong filter in a closed loop, with up to 87% acceptance on correct CloverBench examples and no false positives on the adversarial incorrect ones in that evaluation. The lesson there is not "trust the model" — it is "make the checker honest, explicit, and useful." (arXiv)

The Model Context Protocol is how coding agents reach tools and data sources. X07 ships an MCP kit in x07-mcp, and the x07 CLI hands template scaffolding and conformance tooling off to it.

This walkthrough uses the HTTP template because you can poke at it with curl. Two siblings exist: mcp-server-stdio for stdio transport, and mcp-server-http-tasks when you need long-running task APIs.

Run a small local code model for a while and you notice the failures are rarely about logic. They are about structure. The model gets close, but the output does not parse, the imports drift, a block never closes, or the file shape just is not valid for the target language.

X07 sidesteps that. The canonical source format is x07AST JSON, and the toolchain can export both a JSON Schema and a grammar bundle describing that structure. The docs call that export surface Genpack.

The payoff for local models: constrained decoding can target the language's actual source form, not a best-effort textual approximation of it.

I have spent a lot of time watching coding agents fail in quiet ways.

Not the obvious failures. Not the "I cannot do that" failures.

The quiet ones.

The function that looks clean but uses the wrong boundary encoding. The patch that compiles but drifts away from the repo's architecture. The generated test that passes because the fixture is too weak, not because the code is right.

Those failures changed how I think about programming languages.

X07 is a compiled systems language built around a simple constraint:

coding agents are much more reliable when the language and toolchain stop asking them to improvise at critical boundaries.

Most mainstream languages were optimized for humans carrying context in their heads. Agents work differently. They do better when the source form is canonical, the diagnostics are structured, the effect boundaries are explicit, and the repair loop is deterministic.

That is the design space X07 is exploring.

Series navigation: Previous: Programming With Coding Agents Is Not Human Programming With Better Autocomplete · Post 2 of 3 · Next: How to Trust X07 Code Written by Coding Agents

Most languages are trying to make humans flexible.

X07 is trying to make agents reliable.

That sounds like a small wording difference, but it changes almost everything: the source format, the diagnostics, the execution model, the testing story, the architecture tooling, and even the surrounding ecosystem.

The official X07 docs describe an agent-first systems language, and the current toolchain surface is built around deterministic worlds, record and replay, schema derivation, state machines, property-based testing, function contracts with bounded verification, and review or trust artifacts. That is not an AI plugin bolted onto a normal language. It is a language and toolchain shaped around machine-driven repair loops from the start.