KogniVera
AI Software Development
Framework
ASDF is KogniVera's method for building software with AI agents you can trust. Instead of ad-hoc prompting, every project runs on three governing artifacts — a Constitution that sets inviolable engineering rules, a roster of Agents with crisp scope, and executable Specs that define each unit of work. Agents refuse to write code until the constitution and specs exist; humans review and approve every artifact.
Access is restricted to KogniVera members — sign in to open the builders and your projects.
The Three Phases
Inception
The Constitution sets the technology floor, compatibility, security & compliance. Specs decompose the work.
Construction
Execute specs — the right agent per spec, run in parallel, each with a clear contract.
Operation
Observe, measure, and evolve. Artifacts and metrics keep humans in control of the verdict.
Harness Agnostic
The framework is independent of any single AI harness. The same phases, specs, and agent discipline run on Gemini CLI, Claude Code, OpenCode, Pi, Copilot, and others — some carry a brand implicitly, others are brand-agnostic and let you point them at any model. It even runs fully offline against local models via Ollama. Only minor naming conventions differ between harnesses, and everything works the same.
One playbook, any harness
Constitution, specs, and agent roster stay identical regardless of tool.
Minor naming differences
Harnesses label agents, skills, and config slightly differently — the workflow is unchanged.
Swap without rework
Change harness, or mix several at once, without rewriting your specs or process.
What Can Go Wrong — and How ASDF Prevents It
AI agents fail in predictable ways. ASDF exists because each failure mode has a working countermeasure.
warningWatch out
Ignoring your tech stack
Models default to their favorite stack — they will quietly swap your chosen framework, database, or library for what they saw most in training unless the choice is pinned down in writing.
Hallucinations
Confidently invented APIs, packages that don't exist, config options that were never real. Plausible-looking code is not the same as correct code.
Unrequested scenarios
Agents love to be helpful — extra features, edge cases, and flows nobody asked for creep into the code, growing scope and review surface silently.
Silent assumptions
When a requirement is ambiguous the model picks an interpretation and moves on without telling you. The gap surfaces weeks later as a defect.
shieldGuardrails
Always refer to the constitution
The constitution is the supreme engineering authority. Every agent reads it before writing a line of code — stack, standards, and forbidden choices are pinned there, not in prompts.
Use the right agent for the work
Match each spec to a role-scoped agent — a senior dev engineer for features, a code reviewer for diffs, a security specialist for auth. One generalist agent doing everything is how scope drifts.
Review your git repo constantly
Diff every change the agent makes. Check the repo after each task and make sure the changes are exactly what was requested — nothing more, nothing missing.
Specs with acceptance criteria
Every requirement carries Given/When/Then criteria, and unanswered questions are listed as Open Questions — never invented. If it's not in the spec, it doesn't get built.
Guiding Principles
Specs over prompts
The spec is the reviewable unit of work, not the prompt.
No silent decisions
Every default and assumption is visible, editable, and recorded.
Humans own the verdict
AI drafts; people review, edit, and approve before anything ships.
Foundations
ASDF isn't invented from scratch — these are the ideas it builds on.
Microsoft
Spec-Driven Development: AI-Native Engineering
The spec as the durable, reviewable unit of work in AI-assisted engineering — the core idea behind ASDF's executable specs.
Readopen_in_newAWS
AI-Driven Development Life Cycle (AI-DLC)
Reimagining the SDLC around AI: phased flow, human checkpoints, and AI doing the heavy lifting — mirrored in ASDF's Inception → Construction → Operation phases.
Readopen_in_newGitHub
Spec Kit
GitHub's open-source toolkit for spec-driven development — constitutions, specs, and plans as first-class artifacts that drive coding agents.
Readopen_in_newAnthropic
Building Effective Agents
Patterns for composing reliable agent workflows — why ASDF prefers simple, role-scoped agents with clear contracts over one do-everything agent.
Readopen_in_newAnthropic
Claude Code Best Practices
Agentic coding practices — context files the agent reads first, scoped permissions, and verify-as-you-go review habits ASDF bakes into its guardrails.
Readopen_in_newBMAD
BMAD-Method
Breakthrough Method for Agile AI-Driven Development — specialized agent roles (analyst, PM, architect, dev) collaborating through structured planning documents, kin to ASDF's role-scoped agent roster.
Readopen_in_new