I Ran a Manager-Worker Agent Team on Real Work. A Single Session Beats It.
I ran a manager-worker agent team on 67 real tasks. A single session would have done the work better. The failure modes are structural.
About Lance
Backend Engineer • AI Infrastructure
I'm Lance Rogers, a backend engineer with 11+ years shipping production systems across fintech, security, blockchain, and developer tooling. Today I build AI execution infrastructure: LLM orchestration, MCP, multi-agent systems, and evaluation tooling. I bring the same craft to your team.
What I do
Production AI infrastructure. I built and ship Festival, the camp and fest CLIs that organize agent workflows. The stack is in daily use coordinating 27+ projects in one shared execution environment, with 90%+ token reduction versus unstructured agent runs. I also wrote claude-code-go, the first full-featured Go SDK for Anthropic's Claude Code, shipped within days of API availability.
Open-source Go developer tooling. Beyond Festival and Claude Code Go I've released a steady stream of small Go tools for working with AI and code: tcount (token counter for files and directories, also wired into a Neovim plugin), tree2scaffold (build project layouts from an ASCII tree), gomod-rename (refactor Go module paths cleanly), and algo-scales (open-source CLI for algorithm interview prep with AI tutoring, plus a companion Vim plugin).
Multi-agent and agentic systems. At ETHDenver 2026 I shipped the Obey Agent Economy: five autonomous agents coordinating across Hedera, 0G, and Base. Includes a Go inference agent on 0G's decentralized GPU network with ERC-7857 iNFTs, an autonomous DeFi agent on Base, settlement contracts, and a co-authored HIP-1215 ReputationDecay standard for agent reputation.
Backend at scale. I build production Go and Python backends that handle real load: OTC crypto trading platforms with KYC and compliance workflows, NFT marketplaces handling 15M+ on-chain transactions per month (at Mythical Games) with 100% finality, and custodial wallet services that let non-crypto-native users hold and trade assets without ever seeing a seed phrase.
Modernization in high-control environments. Inside Bank of America's Global Security group I rebuilt a 15-year-old codebase and shipped a CI/CD pipeline that cut deploy cycles from months to hours, reclaiming roughly six developer-months of productivity every year inside one of the most restricted enterprise environments in finance.
How I work
1. Plan first, code once. I spend real time on planning so the v1 deliverable is the right thing built well, not a fast first draft your team has to throw away. Most of the AI tooling I write enforces the same discipline on agents.
2. Systems thinking. I trace features to revenue, latency to user experience, and compliance to risk. That map guides architecture decisions long before any code gets written.
3. Knowledge transfer is part of the job. Clean commits, working docs, and team walkthroughs ship with every engagement. The goal is for your team to keep moving after I leave, not to keep me on retainer.
If your team is paying for AI tools but output is inconsistent, or you have hard backend, blockchain, or AI-infrastructure problems and want a senior engineer who has shipped them before, send a note. I bring engineers, not slide decks.
Experience & Projects
AI & Machine Learning
Festival (fest.build)
Obey Agent Economy
CRE Risk Router
Brainyard
Anywr.ai
Guild Framework
Claude Code Go SDK
YouTube Summarizer
AlgoScales
Bank of America Internal ML Automation
SSI Schaefer Warehouse Optimization
Blockchain & Web3
Shrapnel (Neon Machine)
Investifi
Mythical Games
Dragonchain
Blocksnap
ShinySwap
Swapblocks
Charlotte Blockheads
FinTech & Enterprise
Bank of America
PNC Bank
Global Payments
Shutterfly
Festival (fest.build)
Obey Agent Economy
CRE Risk Router
Brainyard
Anywr.ai
Guild Framework
Claude Code Go SDK
YouTube Summarizer
AlgoScales
Bank of America Internal ML Automation
SSI Schaefer Warehouse Optimization
Shrapnel (Neon Machine)
Investifi
Mythical Games
Dragonchain
Blocksnap
ShinySwap
Swapblocks
Charlotte Blockheads
Bank of America
PNC Bank
Global Payments
Shutterfly
Festival (fest.build)
Creator Sept 2025 - PresentPublic release of the camp and fest CLIs: modular tools for AI workspace management and hierarchical autonomous execution. Users own their data and can swap underlying AI providers without lock-in. Designed around the principle that agents should plan before they execute, track progress as they go, and validate their own work afterward, with correction loops that force them to verify.
Key Features
Pre-execution Planning
fest enforces planning phases before agents start work; goals defined explicitly before any task runs
Impact: Agents know what they're supposed to ship before they start typing, so there are fewer wasted runs and fewer rework loops
Hierarchical Execution
Phase / sequence / task hierarchy gives long-running agent work a structure that survives context resets and session boundaries
Impact: Multi-day or multi-session work stays coherent across agent invocations
Self-Validating Correction Loops
Quality gates at the end of every implementation sequence (testing, review, iteration) that force agents to verify their own work before declaring it done
Impact: Catches the failure mode where agents mark tasks complete without actually shipping the work
Provider-Agnostic, User-Owned Data
Modular CLIs (camp + fest) with Claude Code plugin distribution. Users own their workspace data and can swap AI providers without lock-in
Impact: Works against any AI provider; user data never leaves their environment
Achievements
- In production use coordinating 27+ projects in a single shared execution environment
- Reduced token usage 94% versus unstructured agent runs while maintaining near-100% task accuracy
- Public release at fest.build; open-source CLIs distributed via Claude Code plugin and standalone install
Obey Agent Economy
Creator & Lead Engineer 2026 - PresentETHDenver 2026 stack: a working multi-chain AI agent economy where five specialized agents coordinate across Hedera, 0G, and Base. Demonstrates production-grade agentic architecture: on-chain identity, decentralized inference, autonomous DeFi, observability, and orchestration, all built as open source.
Key Features
Coordinator Agent (Hedera)
Go orchestrator dispatching tasks via Hedera HCS, managing HTS payments and quality gates across the agent fleet
Impact: Single source of truth for cross-chain task dispatch and settlement
Inference Agent (0G)
Go AI inference agent running on 0G's decentralized GPU network, with ERC-7857 iNFTs for provenance and 0G Storage/DA for the audit trail
Impact: Decentralized inference with cryptographic provenance, no centralized model black box
DeFi Agent (Base)
Autonomous Go DeFi agent on Base. Uniswap V3 trading, ERC-8004 identity, x402 payments, ERC-8021 attribution
Impact: Live autonomous trading with full on-chain identity and attribution
Settlement Contracts
Solidity contracts: AgentSettlement, ReputationDecay (HIP-1215 author proposal), ERC-7857 AgentINFT. Full Foundry test suite (34 tests)
Impact: On-chain primitives for agent reputation and settlement; co-author on the HIP-1215 reputation-decay standard
Observer Dashboard
Next.js real-time observer dashboard with 5 live panels: Festival View, HCS Feed, Agent Activity, DeFi P&L, Inference Metrics
Impact: End-to-end visibility across the multi-chain agent economy in one interface
Hiero CLI Plugin
Hiero CLI plugin for camp workspace management with five scaffold templates for Hedera and 0G development
Impact: Reusable scaffolding for the next generation of Hedera + 0G agent builders
Achievements
- Shipped a working five-agent multi-chain economy across three L1/L2 networks
- Co-authored HIP-1215 (ReputationDecay) standard for agent reputation
- Released the entire stack open source as ETHDenver 2026 build
- Demonstrated end-to-end agentic infrastructure with on-chain identity, decentralized inference, and autonomous settlement
CRE Risk Router
Creator 2026Risk-management primitive for autonomous DeFi agents. Eight sequential risk gates evaluate every agent action; each decision is recorded as an immutable receipt via Chainlink's Compute Runtime Environment. Solves the 'how do I trust an autonomous agent with capital' problem with verifiable, auditable risk gating.
Key Features
Eight Sequential Risk Gates
Layered risk evaluation pipeline that every agent transaction must pass before execution
Impact: Failure modes are caught at gate boundaries with clear attribution rather than at runtime with surprise losses
Chainlink CRE Decision Receipts
Each risk decision recorded immutably via Chainlink Compute Runtime Environment for after-the-fact auditing
Impact: Verifiable audit trail: autonomous agent actions become accountable, not opaque
Achievements
- Built a verifiable risk-gating primitive that bridges agent autonomy and capital safety
- Released open source as the on-chain risk layer for the Obey Agent Economy stack
Brainyard
Creator & Lead Engineer Jul 2025 - Jan 2026Production multi-agent chat platform built on top of the Guild orchestration architecture. YAML-based prompt routing with per-agent context windows; demonstrates Guild's primitives in a shipped product.
Key Features
YAML-Based Prompt Routing
Declarative prompt routing config: prompts and agents wired together via YAML with per-agent context windows
Impact: Non-engineers can configure agent routing without touching code
Per-Agent Context Windows
Each agent maintains its own context state and history; conversations route between agents based on intent and capability
Impact: Agents stay within their lane; less context pollution; cleaner conversational handoffs
Achievements
- Shipped as a production multi-agent chat platform
- Validated the Guild orchestration architecture against a real-world product workload
Anywr.ai
Creator Jan 2026Shareable context system for teams: persistent memory and knowledge sharing across LLM sessions. Solves the 'every agent starts from scratch' problem by giving teams a shared knowledge layer that any agent can read from.
Key Features
Persistent Team Context
Shared knowledge layer that persists across sessions and agents; each new conversation starts already knowing the team's facts and decisions
Impact: Teams stop re-explaining the same context to every new chat session
Achievements
- Built and shipped as a production team-context layer for LLM workflows
Guild Framework
Creator & Lead Architect Mar 2025 - PresentPublic source-available collaborative AI agent framework, written in Go, designed around the question: how does a single human direct hundreds or thousands of specialized agents toward one multi-faceted goal? The core orchestration primitives (agent definitions, gRPC inter-agent communication, SQLite + vector memory, multi-layer prompt management, hierarchical 'managers of managers' coordination, and kanban-style task review) are working and underpin the camp/fest CLI ecosystem. Public R&D status: pre-MVP overall; the parts the camp/fest CLIs depend on are battle-tested in daily use.
Key Features
Hierarchical Multi-Agent Orchestration
Specialized agents coordinate via gRPC with task dependencies and a managers-of-managers hierarchy. A single human can direct large agent teams without micromanaging each one
Impact: A working primitive for the 'CEO of a 24/7 agent team' problem
SQLite + Vector Memory Layer
Persistent memory across sessions with vector search; agents share context across runs without re-explaining everything every time
Impact: Agent context survives session boundaries, process restarts, and handoffs between agents
Multi-Layer Prompt Management
Composable prompt system with dynamic context injection and template management; the same prompt patterns work consistently across model providers
Impact: Behavior tuning without rebuilding agent code; provider-agnostic by construction
Accountability via fest CLI
Every agent action is planned before execution and tracked against the plan; quality gates at the end of each implementation sequence force agents to verify their own work and surface mistakes early
Impact: Catches the 'agent marked it done but didn't actually ship it' failure mode before mistakes compound
Achievements
- Public on GitHub under a source-available license at github.com/lancekrogers/guild-core
- Decreased planning time on multi-step hierarchical specs from 1–2 weeks down to ~30 minutes after iterating the framework over six months
- Reduced agent token usage 90%+ versus unstructured runs through templating and just-in-time context injection
- Plans run consistently across model providers; results rarely require human intervention
- Foundation for the camp / fest CLI distribution and the broader Obey ecosystem
Claude Code Go SDK
Author May 2025Go SDK providing a native interface to Claude Code CLI features, enabling developers to build AI-powered applications with Claude's coding capabilities.
Key Features
Full CLI Wrapper
Complete Claude Code CLI wrapper with streaming support and context cancellation
Impact: Native Go interface for Claude Code features
MCP Integration
Model Context Protocol (MCP) integration with multiple output formats (text, JSON, streaming JSON)
Impact: Advanced AI tool integration capabilities
Session Management
Multi-turn conversation support with file processing capabilities
Impact: Production-ready conversational AI features
Cost Optimization
Leverages Claude Max subscription to avoid API costs
Impact: Reduced AI development costs for Go developers
Achievements
- Built comprehensive Go SDK for Claude Code CLI integration
- Implemented streaming support with context cancellation
- Created extensive test suite with unit, integration, and mock server tests
- Provided convenience methods for common AI development use cases
YouTube Summarizer
Creator May 2025CLI tool for summarizing YouTube video transcripts using Ollama for 100% local processing. Supports intelligent transcript extraction, interactive TUI, and research planning features.
Key Features
Local AI Processing
Uses Ollama for 100% local processing without external API keys
Impact: Complete privacy with no external data sharing
Smart Transcript Fetching
Prefers manual captions, supports multiple input formats (.txt, .list, .urls, .csv)
Impact: Flexible input handling with intelligent caption selection
Research Plan Feature
Create focused research plans to extract targeted content across multiple videos
Impact: Comprehensive research document generation from video corpus
Intelligent Processing
Video chunk processing, transcript caching, comprehensive logging
Impact: Efficient processing of long videos with persistent cache
Achievements
- Built privacy-focused YouTube summarization tool with 100% local processing
- Implemented intelligent transcript extraction with manual caption preference
- Created unique research planning feature for multi-video analysis
- Designed for researchers, content creators, and students
AlgoScales
Creator 2025Early-stage open-source algorithm learning tool for coding interview preparation. Built in Go with a terminal-first design to help developers practice 11 fundamental algorithm patterns.
Key Features
Pattern-Based Learning
Organizes coding problems by algorithm patterns (Sliding Window, Two Pointers, etc.) similar to musicians practicing scales
Impact: Structured approach to algorithm pattern recognition
Multiple Practice Modes
Learn, Practice, and Cram modes with progress tracking and daily practice workflow
Impact: Flexible learning experience with built-in accountability
AI Integration
AI-powered hints and explanations using Ollama or Claude Code via custom Go SDK
Impact: Enhanced learning with AI assistance
Editor Integration
Vim plugin for in-editor problem solving, with Neovim and VS Code support planned
Impact: Practice within familiar development environment
Achievements
- Built MVP algorithm practice tool for personal interview preparation
- Implemented Go-based CLI with multi-language support (Go, Python, JavaScript)
- Created Vim plugin for in-editor coding practice
- Integrated AI chat functionality using custom Claude Code Go SDK
Bank of America Internal ML Automation
Contributing Engineer 2017-2018Automated my job by building a neural network using python and numpy to write regular expressions and SQL code based on business requirements.
Key Contributions
Neural Net Data Quality Rule Generator
Generate regular expressions and SQL code based on business requirements
Impact: Reduced workforce requirements
Automated Code Analysis Report Generation
Automated an incredibly tedious business process by building a tool that performed a 3 month excel based analysis in 30 seconds with a button click
Impact: Reduced workforce requirements
Achievements
- Finished 18 month contract work in 6 months
- Delivered tools that automated human processes that cost the bank $4 Million per year
SSI Schaefer Warehouse Optimization
Software Engineer 2016-2017Applied machine learning to robotic warehouse debugging and maintenance scheduling.
Key Contributions
Predictive Analytics
ML models for warehouse efficiency optimization
Impact: Improved maintenance planning, reduced firedrills and system shutdowns
Automation Integration
Integrated ML predictions into warehouse automation systems
Impact: Smarter warehouse operations
Achievements
- Built ML-driven warehouse optimization processes
- Improved operational efficiency through predictive analytics
Shrapnel (Neon Machine)
Blockchain Engineer (via Blockhead Consulting) Contract engagementWeb3 first-person extraction shooter built on GalaChain. Engaged via Blockhead Consulting to own the blockchain backend and custodial wallet service that bridges the Shrapnel game client and the chain that underpins its player-owned economy.
Key Projects
Custodial Wallet Service
Built the custodial wallet service that lets non-crypto-native players hold and trade in-game assets without managing private keys themselves
Impact: Removed the wallet-onboarding friction that kills web3 game adoption. Players never see a seed phrase
GalaChain Backend Services
Backend services bridging the Shrapnel game client and GalaChain: transaction signing, asset state, on-chain settlement for a AAA FPS title
Impact: Production blockchain infrastructure for a shipping AAA web3 game
Local Hyperledger Fabric Tooling
Created local Hyperledger Fabric tooling so blockchain microservices could be exercised against a real-feeling chain in dev and CI without standing up a shared testnet for every engineer
Impact: Accelerated microservice testing turnaround and removed shared-testnet contention from the dev loop
Key Achievements
- Owned the custodial wallet path end-to-end so players experience web3 assets without web3 friction
- Shipped production GalaChain backend for a AAA web3 gaming title
- Built the local Hyperledger Fabric tooling that became the team's standard test harness for chain-touching microservices
Investifi
Senior Backend Engineer Jul 2025 - Feb 2026Led backend development of a white-glove OTC crypto trading platform serving community banks and credit unions. The platform processed $20M+ in trades end-to-end, including KYC verification, trade execution, and the compliance workflow regulated buyers require.
Key Projects
OTC Crypto Trading Backend
Django backend powering the white-glove OTC trade execution path; handled order intake, KYC verification, trade settlement, and the compliance audit trail
Impact: Platform processed $20M+ in trades for regulated financial-institution buyers
Zoho CRM Integration & Internal Dashboards
Wired the trading backend into Zoho CRM and built internal dashboards so the operations team could see deal flow, KYC state, and exception cases in one place
Impact: Operations team had a single source of truth for every trade and KYC artifact
KYC & Automated Fraud Prevention
Built KYC verification flows and automated fraud-prevention checks against the OTC trade pipeline
Impact: Caught suspect trades before settlement; kept the platform inside the compliance envelope its regulated buyers required
Key Achievements
- Built the backend that processed $20M+ in OTC crypto trades
- Owned the KYC, trade execution, and compliance workflows end-to-end
- Integrated the trading platform with Zoho CRM and shipped internal dashboards for operations
Mythical Games
Software Engineer, Blockchain Apr 2022 - Apr 2023Blockchain infrastructure development for gaming-focused NFT marketplace handling millions in transactions per day.
Key Projects
NFT Marketplace Backend
Golang microservices handling on-chain transactions
Impact: 15M+ transactions/month with 100% finality
Smart Contract Development
Solidity contracts for gaming and marketplace features
Impact: Audited contracts deployed to production
Cross-Chain Bridge
NFT bridge architecture to mainnet Ethereum
Impact: Enabled asset portability between networks
Key Achievements
- Discovered critical Polygon Edge bug before mainnet launch, quickly migrated nodes to Hyperledger Besu
- Built highly scalable transaction processing system
- Contributed to protocol-level infrastructure decisions
Dragonchain
Senior Software Engineer Jun 2019 - Jan 2020Developed dApps and blockchain infrastructure for enterprise blockchain platform.
Key Projects
dApp Development Platform
Python/Node.js microservices for rapid dApp prototypes and POCs
Impact: Accelerated client project delivery
Cross-Chain Hackathon Platform
Architected platform with weighted voting using time-held coins
Impact: Novel governance mechanism implementation
Den Social Platform
Smart contracts and Go backend for decentralized social media
Impact: Production social media dApp
Key Achievements
- Built multiple production dApps for enterprise clients
- Contributed to core blockchain platform development
- Designed innovative consensus and governance mechanisms
Blocksnap
Creator Feb 2022NFT data intelligence tool built at EthDenver. Aggregated NFT marketplace data and surfaced patterns about collections, holders, and sale velocity in a single interface. Recognized at the hackathon as a 3rd place community winner.
Key Features
NFT Data Aggregation
Pulled and normalized data across NFT marketplaces and on-chain sources to give holders and traders a single intelligence view
Impact: Surfaced collection-level signals that were otherwise scattered across marketplaces
Achievements
- EthDenver 2022 hackathon, 3rd place community winner
- Shipped a working NFT intelligence prototype within hackathon time constraints
ShinySwap
Architect & Lead Developer Apr 2023 - PausedPersonal project building distributed exchange for physical precious metals trading with DeFi integration.
Key Features
P2P Exchange Architecture
Distributed system for peer-to-peer precious metals trading
Impact: Enabled physical asset liquidity access
Secure Escrow System
On-site verification system for physical asset trades
Impact: Trustless trading of physical assets
DeFi Integration
Bridge to use physical metals in DeFi protocols
Impact: Novel asset class for DeFi
Achievements
- Designed innovative physical-digital asset bridge
- Built secure verification and escrow systems
- Created novel DeFi integration patterns
Swapblocks
Founder/Developer February 2018 - July 2019Designed and developed a subnet blockchain network for automating complex asset transfers with signficant regulatory documentation requirements.
Key Features
Custom Smart Contract Engines
Consortium subnets chose the best contract engine for their particular use case.
Impact: No reliance on niche developers for implementation.
Achievements
- 8000 Member Discord Community
- $10M Marketcap
- 48 Community Run Nodes
- 5 Person Team Paid in SBX Tokens
Charlotte Blockheads
Organizer Sept 2017 - Mar 2020Founded and led major cryptocurrency meetup group in Charlotte, North Carolina.
Achievements
- Built community of 8000+ blockchain enthusiasts and developers
- Provided entry point for many into crypto/blockchain space
- Established Charlotte as a blockchain hub in the Southeast
Bank of America
Senior Software Engineer (Contract) Feb 2024 - Dec 2024Led modernization efforts for one of America's largest financial institutions, focusing on enterprise CI/CD infrastructure and legacy security scanning systems.
Key Projects
CI/CD Pipeline Modernization
Designed and implemented CI/CD pipeline for 15-year-old codebase
Impact: Reduced deploy times from months to hours
Security Scanning Refactor
Modernized legacy Python security scanning software
Impact: Ensured compliance with modern secure coding standards
Developer Productivity Initiative
Automation and process improvements
Impact: Reclaimed 6+ months/year of lost developer time
Key Achievements
- Resolved long-standing security blockers by sanitizing over a decade of sensitive Git history
- Led modernization efforts including documentation, release process automation, and cross-team tooling
- Improved sprint velocity through strategic automation initiatives
PNC Bank
Software Engineer Consultant 2018Conducted comprehensive audit of data processing pipelines for major regional bank.
Key Projects
Pipeline Security Audit
Comprehensive security and accuracy audit of Python data pipelines
Impact: Found coding errors missed in an OCC remediation effort affecting thousands of customers
Key Achievements
- Identified and resolved critical security vulnerabilities in data processing
- Improved data accuracy through pipeline optimization
- Delivered comprehensive security recommendations
Global Payments
Software Engineer Consultant 2019Performance optimization of data processing systems for payment processing company.
Key Projects
ETL Optimization
Performance tuning and cost optimization of ETL processes
Impact: Cut AWS spend by $40K/month
Key Achievements
- Achieved 80% reduction in cloud infrastructure costs
- Improved data processing throughput by 3x
- Implemented cost monitoring and alerting systems
Shutterfly
Software Engineer (Contract) Feb 2020 - Feb 2021Worked on order processing systems for one of the largest photo commerce platforms.
Key Projects
Forge Workflow Enhancement
Enhanced Python-based order workflow engine routing online orders to factory processes
Impact: Improved order processing reliability and throughput
AWS Migration Support
Assisted in migration planning of Forge from on-prem servers to AWS
Impact: Modernized infrastructure for better scalability
Key Achievements
- Improved system reliability and reduced downtime
- Enhanced order routing efficiency
See What I'm Working On Now
Recent Activity
Latest Technical Insights
Your Agent's Memory Should Be Files in Git, Not Rows in a Vendor's Database
Agent memory should be files in git, next to the work they describe, not rows in a vendor database.
Quality Gates for Agent Work: Decisions, Not Formalities
A gate an agent waves itself through is not a gate. Quality gates for agent work have to be decisions against artifacts.
Ready to Build Something Great?
Let's discuss how my experience can help accelerate your project.