Workspace/Mini projects
Loading progress
TURN A MECHANISM INTO A SYSTEM

Mini projects

One build per module. Start with running code, add the missing capabilities, and prove the result.

0/32 marked complete
MODULE 01 · Python

Contract-first ingestion runner

Build an ingestion tool that receives fixture responses, validates each record, preserves failures, and emits a reproducible run envelope that a frontend could consume.

MODULE 02 · Vectors

Escalation threshold decision report

Build an offline evaluation report that chooses an escalation threshold on validation examples, reports error costs and workload, and evaluates a frozen choice on a separate test fixture.

MODULE 03 · Neural networks

A tiny network you can audit

Build a small neural-network trainer whose forward pass, derivatives, and loss trajectory can all be inspected without a machine-learning framework.

MODULE 04 · Tokenization

Transformer resource worksheet

Build a reproducible resource report that compares cache layouts, prompt/output reservations, and idealized concurrency under an explicit memory budget.

MODULE 05 · Responses API

Replayable model adapter

Build a model-integration adapter with an offline replay mode, explicit tool execution, strict result validation, and observable completion states.

MODULE 06 · Agents

Catalog agent workbench

Build a small local interface for a bounded catalog assistant, with a shared controller usable from a CLI and HTTP API and a visible evidence-backed run result.

MODULE 07 · Python

Reservation gateway with an audit trail

Build a local reservation gateway that separates request envelopes, validation, authorization, and domain effects. Deliver a runnable CLI simulation plus documented production boundaries.

MODULE 08 · MCP

MCP boundary inspector

Build an inspector that explains why recorded tool attempts were accepted, rejected, or left uncertain, then connect it to one verified MCP server revision.

MODULE 09 · Planning

Evidence-led incident planner

Build a local incident planner that creates observable actions, consumes fixture observations, revises remaining work, and verifies the final diagnosis.

MODULE 10 · Architecture

Inspectable incident control loop

Build a small controller with typed observations, working state, memory lookup, strategy choice, execution simulation, and a decision record for every action.

MODULE 11 · Memory

Memory lifecycle workbench

Build a local memory workbench with typed records, scoped retrieval, corrections, deletion, expiry, and a provenance view showing which summaries depend on which records.

MODULE 12 · RAG

Grounded configuration answer service

Build a local retrieval service over versioned configuration notes, with hybrid candidate fusion, explicit evidence bundles, and claim-level support checks.

MODULE 13 · Knowledge graphs

Temporal dependency evidence explorer

Build a reproducible evidence explorer that answers which teams were connected to a deprecated dependency at a specified time, then evaluates passage and graph retrieval on labeled questions.

MODULE 14 · Multiagent

Recoverable release review coordinator

Build a small coordinator that executes independent review tasks, persists task outputs, and recovers without duplicating a final external action. The seed is an in-memory recovery simulation.

MODULE 15 · Browser agents

Inspectable invoice browser workflow

Build a browser workflow harness that records observations, proposals, preconditions, and persisted outcomes. The seed simulates a tiny invoice application without a browser or network.

MODULE 16 · Computer use

Multimodal command evidence ledger

Build a timeline that joins spoken commands to screen observations and emits reviewable action proposals, retaining uncertainty when evidence is stale or missing.

MODULE 17 · Slack

Channel inbox and response router

Build a normalized inbox that admits one job per namespaced event and prepares channel-specific response drafts. The seed uses local envelopes and sends no messages.

MODULE 18 · A2A

Versioned collaborator gateway

Create a local gateway that selects an approved compatible collaborator, checks tenant and scope policy, and records task progress and accepted artifacts. The seed is a protocol teaching simulation.

MODULE 19 · A2UI

Review surface with synchronized proposal state

Build a constrained generated review surface and a state reducer that rejects stale approvals. The seed combines local UI descriptions with local event state and prints a review preview.

MODULE 20 · Event streams

Proactive incident proposal engine

Build an event-driven monitor that deduplicates failures, groups them into evidence windows, and creates versioned review proposals. The seed prepares proposals and performs no external notification.

MODULE 21 · Reliability

A booking recovery journal

Build a reproducible simulator for reservations, payment capture, ticketing, and compensation. Produce an event journal and a crash-point recovery matrix that explain every externally visible effect.

MODULE 22 · Security

A capability broker with an approval inbox

Build a local action broker for a synthetic report assistant. Its artifact is a policy decision journal and a review screen or command that shows the exact action before approval.

MODULE 23 · Model routing

A routing replay and economics report

Build an offline replay tool comparing routing policies on identical tasks. Produce a report of task success, spending, escalation, and latency distribution with every synthetic assumption visible.

MODULE 24 · Evaluation

A reproducible agent change review

Build an evaluation runner and report for an original task dataset. The deliverable must connect a proposed agent change to paired outcome evidence, cost, uncertainty, and documented limitations.

MODULE 25 · Coding agents

A patch evidence workbench

Build a local workbench that indexes Python source, proposes impacted tests, and assembles a review packet containing the reproduction, patch, instructions used, and verification results.

MODULE 26 · Queues

A recoverable report-job service

Build a service that accepts report jobs, executes them in separate workers, checkpoints progress, and survives documented failures without duplicate publication. Deliver code, deployment instructions, and a failure-drill report.

MODULE 27 · Datasets

Adaptation readiness report

Create a preflight report that combines dataset lineage, retained task coverage, protected-group checks, and adapter memory estimates before a training job is approved.

MODULE 28 · RL

Reward shortcut audit bench

Build a small evaluation bench that exposes candidates which score highly under a proxy reward while failing an independent task criterion.

MODULE 29 · Inference

Serving capacity notebook without a GPU

Produce a reproducible capacity report that combines architecture-level cache math, page reservations, and scenario comparisons, then defines a future measured load test.

MODULE 30 · Privacy

Tenant isolation regression pack

Create a synthetic regression pack and evidence report for a multitenant agent boundary, including cross-tenant access, scope errors, expiry, and benign utility.

MODULE 31 · Research

A reproducible experiment dossier

Build a compact research artifact that states a falsifiable hypothesis, compares paired outcomes, records lineage, and supports a bounded conclusion.

MODULE 32 · System design

Evidence desk: an integrated agent capstone

Deliver a tenant-aware incident evidence desk with a usable task interface, an MCP capability service, an A2A specialist integration, evaluation, operational controls, and a truthful repository report.

Seeds demonstrate a working core. Completing a project means implementing its milestones and acceptance checks, not just downloading the seed.