Atomizer/docs/hq/03-ROADMAP.md

🗺️ Roadmap — Atomizer Overhaul: Framework Agentic

Phased implementation plan. Start small, prove the pattern, scale systematically.

---

Timeline Overview

Phase 0: Proof of Concept     [Week 1-2]     3 agents, basic routing, dedicated Slack
Phase 1: Core Team             [Week 3-4]     6 agents, full planning + study build cycle  
Phase 2: Specialists           [Week 5-7]     10 agents, full pipeline
Phase 3: Full Company          [Week 8-10]    13 agents, all capabilities
Phase 4: Optimization          [Ongoing]      Polish, performance, learning

---

Phase 0: Proof of Concept (Week 1-2)

Goal: Prove multi-agent orchestration works in Clawdbot + Slack.

Tasks

#	Task	Owner	Est. Time	Status
0.1	Create dedicated Slack workspace "Atomizer Engineering"	Antoine	30 min	⏳ Waiting
0.1b	Create channels: #hq, #secretary	Antoine	15 min	⏳ Waiting
0.1c	Create Slack app + get tokens (see README-ANTOINE)	Antoine	20 min	⏳ Waiting
0.1d	Install Docker on T420	Antoine	10 min	⏳ Waiting
0.2	Set up 3 agent workspaces: Manager, Secretary, Technical Lead	Mario	2-3 hours	✅ Done (2026-02-08)
0.3	Write SOUL.md + AGENTS.md + IDENTITY.md + USER.md + TOOLS.md for each	Mario	2-3 hours	✅ Done (2026-02-08)
0.4	Create atomizer-protocols shared skill (with real protocols)	Mario	2-3 hours	✅ Done (2026-02-08)
0.4b	Create atomizer-company shared skill (identity + LAC_CRITICAL)	Mario	1 hour	✅ Done (2026-02-08)
0.4c	Write new protocols: OP_09, OP_10, SYS_19, SYS_20	Mario	1 hour	✅ Done (2026-02-08)
0.5	Write docker-compose.yml + clawdbot.json config	Mario	1-2 hours	✅ Done (2026-02-08)
0.5b	Write .env.template + Windows job watcher script	Mario	30 min	✅ Done (2026-02-08)
0.6	Plug in tokens, boot Docker, test routing	Mario + Antoine	1 hour	⏳ Blocked on 0.1
0.7	Test: Manager delegates to Technical	Both	1 hour	⏳ Blocked on 0.6
0.8	Test: Secretary summarizes for Antoine	Both	1 hour	⏳ Blocked on 0.6
0.9	Run one real engineering problem through the system	Both	2-3 hours	⏳ Blocked on 0.7
0.10	Retrospective: what worked, what didn't	Both	1 hour	⏳ Blocked on 0.9

Implementation Progress

Mario's work: 100% complete (2026-02-08)

• All at /home/papa/atomizer/
• 35+ files: workspaces, skills, config, docker-compose, protocols, scripts

Blocked on Antoine:

1. Install Docker on T420 (sudo apt install docker.io docker-compose-v2 -y)
2. Create Slack workspace + app (manifest in README-ANTOINE)
3. Provide tokens (xoxb + xapp + channel IDs)

Success Criteria

• 3 agents respond correctly when @-mentioned in Slack
• Manager successfully delegates a breakdown task to Technical
• Secretary correctly summarizes and relays to Antoine
• Memory persists across agent sessions
• No routing confusion (messages go to right agent)

Key Decisions — ALL RESOLVED ✅

• ✅ Project channels → Manager (fallback binding catches all unbound channels)
• ✅ Single bot token, per-agent identity via chat:write.customize (DEC-A013)
• ✅ Shared skills for company DNA, per-agent SOUL/AGENTS/MEMORY for specialization

---

Phase 1: Core Team (Week 3-4)

Goal: Full planning cycle — intake through study build and optimization launch.

New Agents

• ⚡ Optimizer
• 🏗️ Study Builder
• 🔍 Auditor

Tasks

#	Task	Owner	Est. Time	Dependencies
1.1	Set up Optimizer + Study Builder + Auditor workspaces	Mario	3 hours	Phase 0
1.2	Write SOUL.md + AGENTS.md with LAC critical lessons	Mario	4-5 hours	1.1
1.3	Create atomizer-spec skill for Optimizer + Study Builder	Mario	2 hours	—
1.4	Migrate LAC critical lessons to Optimizer's + Study Builder's MEMORY.md	Mario	1 hour	1.2
1.5	Create Auditor's review checklist protocol	Mario	2 hours	—
1.6	Seed Study Builder with V15 run_optimization.py as gold template	Mario	1 hour	1.1
1.7	Test full planning cycle: problem → breakdown → algorithm → study code	Both	3-4 hours	1.1-1.6
1.8	Test Auditor review of optimization plan + study code	Both	1-2 hours	1.7
1.9	Run a real optimization job through the system (code → Windows → results)	Both	4-8 hours	1.7
1.10	Retrospective	Both	1 hour	1.9

Success Criteria

• Technical Lead → Optimizer → Study Builder handoff works smoothly
• Study Builder produces valid run_optimization.py from Optimizer's design
• Optimizer produces valid AtomizerSpec from Technical's breakdown
• Auditor catches at least one issue in the plan or code
• < 30 minutes from problem statement to approved optimization plan
• Study code syncs to Windows and runs successfully
• All agents stay in character and follow protocols

---

Phase 2: Specialists (Week 5-7)

Goal: Full pipeline from intake to client-ready deliverable. R&D channels operational.

New Agents

• 🖥️ NX Expert
• 📊 Post-Processor
• 📝 Reporter
• 🗄️ Knowledge Base

New Channels

• #audit-log, #knowledge-base
• First R&D channel: #rd-<topic> (Antoine picks)

Tasks

#	Task	Owner	Est. Time	Dependencies
2.1	Set up 4 specialist workspaces	Mario	3 hours	Phase 1
2.2	Write specialized SOUL.md + AGENTS.md	Mario	4-6 hours	2.1
2.3	Create NX reference skill from existing docs	Mario	3-4 hours	—
2.4	Create post-processing skill (extractors, Zernike)	Mario	3-4 hours	—
2.5	Integrate atomaste-reports skill for Reporter	Mario	1 hour	—
2.6	Integrate cad-documenter skill for KB Agent	Mario	1 hour	—
2.7	Test full pipeline: intake → report	Both	6-8 hours	2.1-2.6
2.8	Test KB Agent processing CAD Documenter output	Both	2-3 hours	2.6
2.9	Test Reporter generating Atomaste PDF	Both	2-3 hours	2.5
2.10	Run 2-3 real projects through full pipeline	Both	Multi-day	2.7
2.11	Retrospective	Both	1 hour	2.10

Success Criteria

• NX Expert provides solver config that Optimizer can use
• Post-Processor generates visualizations from real results
• Reporter produces client-ready PDF report
• KB Agent successfully indexes a CAD Documenter walkthrough
• End-to-end: client problem → approved report in < 1 day (FEA time excluded)

---

Phase 3: Full Company (Week 8-10)

Goal: Complete ecosystem with all support roles.

New Agents

• 🔬 Researcher
• 💻 Developer
• 🛠️ IT Support

Tasks

#	Task	Owner	Est. Time	Dependencies
3.1	Set up remaining 3 workspaces	Mario	2 hours	Phase 2
3.2	Write specialized SOUL.md + AGENTS.md	Mario	3-4 hours	3.1
3.3	Configure Researcher with web_search + Gemini	Mario	1-2 hours	3.1
3.4	Configure Developer with Git access	Mario	1-2 hours	3.1
3.5	Test Researcher literature search workflow	Both	2 hours	3.3
3.6	Test Developer coding + PR workflow	Both	2 hours	3.4
3.7	Full company stress test: complex multi-phase project	Both	Multi-day	All
3.8	Cost analysis and optimization	Mario	2 hours	3.7
3.9	Retrospective + full documentation	Both	2-3 hours	3.8

Success Criteria

• All 13 agents operational and in-character
• Researcher provides useful literature for optimization method selection
• Developer successfully codes and tests a new extractor
• System handles a complex project with multiple specialists involved
• Per-project cost within acceptable range ($20-40)
• Antoine's time per project < 20% (rest is agents)

---

Phase 4: Optimization (Ongoing)

Goal: Continuous improvement of the company.

Continuous Tasks

Task	Frequency	Owner
Review and update agent MEMORY.md files	After each project	Each agent
Update protocols based on lessons learned	Monthly	Manager + Antoine
Review token usage and optimize context sizes	Bi-weekly	Mario
Improve agent SOUL.md based on behavior	As needed	Mario + Antoine
Add new skills as capabilities expand	As needed	Developer + Mario
Cross-train agents (share insights between roles)	Monthly	Manager

Future Enhancements (Not Blocked On)

Enhancement	Priority	Effort	Notes
MCP server integration	Medium	High	Agents access Atomizer via MCP tools
Voice interface (Whisper live)	Low	Medium	Antoine talks, agents listen
Dashboard integration	Medium	High	Agents control dashboard directly
Automated project channel creation	Medium	Low	Manager creates channels via API
Client portal	Low	High	Clients interact directly with system
Agent performance metrics	Medium	Medium	Track quality, speed, token usage per agent

---

Resource Requirements

Hardware

• Current Clawdbot server — should handle 13 agents (they're not all active simultaneously)
• Disk: ~500MB for agent workspaces + session storage
• RAM: Monitor after Phase 1; may need increase for concurrent agents

API Budget

• Phase 0: ~$50/month (3 agents, testing)
• Phase 1: ~$100-150/month (6 agents, real projects)
• Phase 2: ~$200-250/month (10 agents, full pipeline)
• Phase 3: ~$300-400/month (13 agents, full operations)
• Steady state: Depends on project volume; ~$25-40 per client job

Time Investment

• Phase 0: ~15-20 hours (Mario: ~12h, Antoine: ~5h)
• Phase 1: ~20-25 hours (Mario: ~15h, Antoine: ~8h)
• Phase 2: ~30-40 hours (Mario: ~25h, Antoine: ~12h)
• Phase 3: ~20-25 hours (Mario: ~15h, Antoine: ~8h)
• Total: ~85-110 hours over 10 weeks

---

Immediate Next Steps

✅ COMPLETED (Mario — 2026-02-08)

• Set up Phase 0 agent workspaces (Manager, Secretary, Technical Lead)
• Write SOUL.md, AGENTS.md, IDENTITY.md, USER.md, TOOLS.md, MEMORY.md for each
• Create atomizer-protocols shared skill with all 17 real protocols + 4 new ones
• Create atomizer-company shared skill with identity + LAC_CRITICAL.md
• Write docker-compose.yml and clawdbot.json multi-agent config
• Write .env.template for token management
• Write Windows job watcher script (atomizer_job_watcher.py)
• Create job queue directory structure
• Write README-ANTOINE with full step-by-step setup guide

All files at: /home/papa/atomizer/

✅ COMPLETED (Antoine — 2026-02-08)

• Created Slack workspace: Atomizer HQ (atomizer-hq.slack.com)
• Created Slack app with manifest
• Created channels: #all-atomizer-hq, #secretary
• Provided tokens to Mario

✅ COMPLETED (Mario — 2026-02-08, afternoon)

• Pivoted from Docker to native second gateway (no Docker image available)
• Gateway running on port 18790 with state dir ~/.clawdbot-atomizer/
• Slack Socket Mode connected to Atomizer HQ workspace
• Channel bindings configured: Manager → #all-atomizer-hq, Secretary → #secretary
• Auth profiles shared (same Anthropic OAuth)
• Shared skills symlinked into state dir

🟢 Phase 0 LIVE — Current Status (2026-02-08 18:00 UTC)

• Gateway: Running natively at port 18790
• Agents active: Manager (🎯), Secretary (📋), Technical Lead (🔧)
• Slack connected: Atomizer HQ workspace
• Tools: All standard Clawdbot tools (read, write, exec, web_search, etc.)
• Skills: atomizer-protocols (21 protocols), atomizer-company

⏳ NEXT: Phase 0 Validation

1. Test Manager orchestration in #all-atomizer-hq
2. Test Secretary reporting in #secretary
3. Run a real engineering problem through 3-agent system
4. Validate memory persistence across sessions
5. Retrospective → tune SOUL.md and protocols

🔜 Phase 1 Prep (after Phase 0 validated)

1. Add 3 new agents: Optimizer, Study Builder, Auditor
2. Create workspaces + SOUL/AGENTS files
3. Update gateway config with new agent entries + bindings
4. Seed Study Builder with V15 gold template
5. Migrate LAC lessons to agent memories

---

Created: 2026-02-07 by Mario Updated: 2026-02-08 — Phase 0 LIVE, gateway running, 3 agents operational