AI & ML interests

CRAFT applies structured programming principles to AI conversations. Think recipes for your workflows.

CRAFTFramework 
posted an update 17 days ago
view post
Post
119
# CRAFT Session Handoffs: Solving the Stateless AI Collaboration Problem

AI desktop tools like Claude Cowork are increasingly capable for multi-session projects — but they're architecturally stateless. Each session starts with an empty context window, losing all prior decisions, file states, and project context. The human becomes a manual bridge between sessions.

## Approach: Structured Handoff Protocol

CRAFT addresses this with a multi-format handoff protocol that captures complete session state in structured text files. At session end, a handoff recipe records accomplishments, decisions, file manifests, git state, active priorities, open questions, lessons learned, and persona configuration. At session start, an initialization recipe reads the latest handoff and restores full context.

The system uses four purpose-built recipes: Session Initialization (CWK-001), Direct Handoff (CWK-002), Device-Switch Handoff (CWK-002a), and Mid-Session Checkpoint (CWK-003). A two-layer initialization architecture — static CLAUDE.md bootstrap plus dynamic recipe state — provides redundancy against stale components.

A 4-layer propagation chain ensures persistent behavioral directives survive across sessions and framework updates: CLAUDE.md, project file, generator template, and enforcement recipe.

## Empirical Results

The system was validated during CRAFT's own development: 71 consecutive handoffs (H001–H071) with zero data loss. The handoff protocol survived 5+ context compaction events, multiple application crashes, and a cross-device transfer. Each session relied on the previous session's handoff for complete context restoration.

## Key Design Decisions

Handoff files are stored as structured plain text on the user's local machine — no cloud dependency, full data ownership. The handoff itself triggers an automatic git commit, providing version history of the project's session state over time.

Free public beta: [github.com/CRAFTFramework/craft-framework]
CRAFTFramework 
posted an update 23 days ago
view post
Post
74
CRAFT Framework: Structured AI Session Management for Claude Cowork — Free Public Beta

Overview

CRAFT (Configurable Reusable AI Framework Technology) is a structured communication framework that provides persistent session continuity, version control integration, and systematic quality assurance for AI-assisted workflows running on Claude's Cowork desktop platform.

Technical Architecture

CRAFT uses a recipe-based system — 188 standardized workflow definitions across 12 cookbooks — to manage the full lifecycle of AI project sessions. Key subsystems:

- **Session Handoff System (4 recipes):** Structured state serialization that captures project context, decision history, and persona calibration between sessions. Validated across 71 consecutive handoffs with zero information loss over 72 development sessions.
- **Version Control Integration (4 recipes):** Event-driven git checkpoints triggered by workflow completion rather than time intervals. Maintains over 500 files across 9 projects in a unified monorepo.
- **Quality Assurance Framework (6 recipes, 14-point plan):** Includes 4 verification gates — file pointability, read-vs-reconstructed detection, constraint conflict analysis, and untested assumption identification. Addresses the systematic overconfidence problem in LLM output.
- **Multi-Persona Collaboration (5 recipes):** Separate AI personas for content generation, validation, and operations management. The Creator/Validator pattern enforces independent review.
- **Cross-Project Transfer (4 recipes):** Knowledge packaging with provenance tracking, enabling verified intelligence sharing between project contexts.

Scale

The framework grew from ~60 pre-existing recipes to 188 (213% increase) during a 72-session adaptation project. Development produced 7 formal specifications, 64 documented lessons learned, and ~59,000 lines of recipe content.
CRAFTFramework 
posted an update about 1 month ago
view post
Post
126
Quick observation from working with Claude Cowork on multi-session projects.

**The constraint:** Cowork runs in a sandboxed VM that resets between sessions. No state persistence, no conversation carryover, no cross-session memory. Each session starts with zero context about prior work.

https://craftframework.ai/the-hidden-cost-of-session-amnesia-why-context-matters-more-than-you-think/


Within a single session, context compaction occurs as conversations approach the token limit — the system summarizes earlier exchanges, trading detail for capacity. Decisions made early in a session degrade to single-sentence summaries as the conversation grows.

**The cost:** For task-based work (summarize this, debug that), this is irrelevant. For cumulative work — projects that build over days or weeks — it creates significant overhead. Users spend meaningful time each session re-establishing context that the AI previously held.

**Common workarounds observed:**
- Manual context injection (copy-paste at session start)
- Single mega-sessions (avoids reset, but context degrades)
- External state documents (maintained alongside the AI)

Each trades one form of overhead for another.

**The architectural question:** Claude's chat interface (claude.ai) now has persistent memory — free for all users since March 2026. But the desktop environment still operates on a session-reset model. The gap between chat-based memory and desktop-based amnesia is growing.

This seems like a general problem for desktop AI tools, not just Cowork. How are others approaching session continuity in local AI environments?
  • 1 reply
·
CRAFTFramework 
posted an update about 2 months ago
view post
Post
239
Did you know 78% of employees who use AI bring their own unapproved tools to work? Two studies, same number.CRAFT stores AI workflows as local text files — no platform, no data risk, works with any AI tool.Beta: craftframework.ai
CRAFTFramework 
posted an update 2 months ago
view post
Post
165
87% of organizations experienced SaaS data loss in 2024. 79% of IT teams wrongly assumed their apps had built-in backup.

CRAFT Framework stores AI workflows as plain text files on your machine. No SaaS dependency. No centralized point of failure. Backup = copying a folder.

Beta is open → craftframework.ai
CRAFTFramework 
posted an update 2 months ago
view post
Post
175
CRAFT Framework Beta — What Clicked
Three Pre-Beta messages that resonated with the AI community:
1. No code required to structure AI workflows
2. Classification Tax: privacy solved at the architecture level
3. Your best AI conversations become reusable templates
50+ projects built. Beta now open.
→ craftframework.ai
CRAFTFramework 
posted an update 3 months ago
view post
Post
170
Meta-proof: CRAFT built CRAFT 🍳6 projects, 14 working days → complete brand + website + marketing campaign Key insight: The model matters less than the structure. 56 connected chats = most important info from ~28,000 pages, instantly accessible. One project (048) created 72 pieces of promotional content. This post was built using CRAFT. Not smarter AI—structured AI. Beta open: craftframework.ai/register/founding-chef/
CRAFTFramework 
posted an update 3 months ago
view post
Post
218
🍳 CRAFT Beta: 6 days away OOP principles for AI workflows—but no coding required. Save your best AI conversations as reusable recipes. Works with any AI platform. Developers and non-developers welcome. No code? No problem. CRAFTFramework.ai
CRAFTFramework 
posted an update 3 months ago
view post
Post
205
CRAFT Framework Beta: 13 days Final week of Pre-Beta. 70+ weeks solo development → community testing February 1. OOP principles for AI workflows. Privacy by architecture. Founding Chef status for all Beta members. CRAFTFramework.ai
CRAFTFramework 
posted an update 3 months ago
view post
Post
1083
CRAFT Framework Beta: 20 days awayApplying OOP to AI workflows—recipes, cookbooks, and persistent context across sessions.70+ weeks of solo development. February 1: community testing begins.Founders get permanent recognition + influence on development.CRAFTFramework.ai
CRAFTFramework 
posted an update 4 months ago
view post
Post
1329
🔧 Behind the Scenes
CRAFT development: Sun-Mon only (full-time job Wed-Sat). 48 projects completed solo.
The time constraint is the proof—if the methodology works under pressure, it works.
Beta: February 2026 → craftframework.ai
CRAFTFramework 
posted an update 4 months ago
view post
Post
152
Getting Started with CRAFT
No coding required. CRAFT uses programming metaphors, not programming skills.
Your first recipe: Pick a repeated task. Define what, context, and output. Build once, reuse forever.
Beta: February 2026 → craftframework.ai
CRAFTFramework 
posted an update 4 months ago
view post
Post
203
📈 The CRAFT Journey - From napkin sketch to 48 projects.
CRAFT Framework emerged from 70+ weeks of public AI experimentation on Ketelsen.ai. Not theory—documented work you can verify.
April 2025: POC started
July 2025: Alpha launched
Now: Project 48
One person, 70+ weeks, discovering what works—so you don't have to.
Beta: February 2026
→ craftframework.ai
CRAFTFramework 
posted an update 4 months ago
view post
Post
234
CRAFT Framework architecture explained:
Recipes = parameterized prompts (like functions)
Cookbooks = organized collections (like modules)
Handoffs = session state persistence
Variables = cross-session context
Personas = communication adapters
Works across Claude, ChatGPT, Gemini, and more. Beta Feb 1, 2026.
CRAFTFramework 
posted an update 5 months ago
view post
Post
174
🔐 The AI Privacy Trade-Off

57% say privacy is biggest AI barrier (IBM). 48% share company data anyway (Cisco).

CRAFT Framework: privacy through architecture, not policy.

Beta: February 2026
Follow → craftframework.ai
  • 1 reply
·