Etcetera

Etcetera

AI / Agent Engineer

Summary

Agentic full-stack engineer with 4 years of shipping experience across Agent Skills, Harness, Memory, RAG and cross-platform clients. I focus on AI software systems that are observable, recoverable and continuously iterated, not one-off prompt demos.

Experience2023.04 - present · agentic systems, cross-platform clients, engineering velocity

2023 Product engineering

Started in low-code SaaS, mobile H5 and map-heavy business UI, building delivery rhythm and engineering standards first.

2024 Client reliability

Moved into quant desktop work where build speed, release flow and error context became product stability work.

2025 Agentic systems

Shifted the center of gravity to Skills, Harness, Memory and RAG so model capability lands inside auditable runtime loops.

DCS procurement AI workflow

· procurement AI workflow workflow design / full-stack
Role
Hotel procurement workflow covering bid collection, review scoring, contract review and archival audit, spanning the agent runtime, backend services and the React workbench.
Actions
  • Orchestrated supervisor and specialist agents across technical, commercial and contract review.
  • Combined supply-chain, negotiation and legal-compliance perspectives in the review logic.
  • Delivered structured output, review summaries and persistent run logs for replay.
Impact
Moved procurement review into an auditable multi-agent decision loop with online model tuning, run-cost traceability, and recoverable context across interruptions and reruns.

Etyon desktop AI workbench

· desktop AI workbench agent runtime / desktop
Role
Desktop AI workbench for local development and knowledge workflows, spanning the agent harness, chat runtime, project context and local CLI integration.
Actions
  • Built a harness layer on the AI SDK, Hono and Electron path, separating model calls, context building, tool execution, permission approval, sub-agent delegation, event logs and project snapshot indexing into observable modules; connected Skills, Memory, @ file mentions and the Rust CLI.
  • Designed the workspace tool surface across read, grep, find, bash, edit, write, LSP inspect and web search, controlled by permission policy, sandbox boundaries and secret-path protection.
  • Used event sourcing as the single source of truth (runs, events, tool calls, approvals and artifacts in separate tables), keeping chat history as a UI projection — enabling approval resume, active-run recovery and desktop / CLI entry points.
  • Distilled a reusable Vite+ and Electron desktop scaffold along the way (main/renderer structure, build, packaging, CLI integration, i18n and project checks).
Impact
Moved a chat client toward a recoverable local agent harness with tool traces, approval resume, queued-message replay, cross-project context retrieval and desktop / CLI entry points.

Internal knowledge agentic system

· agentic product direction lead
Role
Agentic chat and spaced-review system for knowledge management, spanning the web app, iOS surface, retrieval backbone, graph context and rich-text editing.
Actions
  • Designed sandbox-approved tool calls so the model can read and write business data safely.
  • Rebuilt hybrid retrieval across FTS, title match, tag inverted index, ILIKE and an LLM reranker.
  • Turned /ref and tags into xyflow-backed graph context for multi-hop reasoning.
Impact
Covered 5 core product loops and made retrieval thresholds, token / character budgets and wasTruncated markers observable enough to control BYOK context cost.

Cursor hackathon · AI coding agent

· AI coding harness architecture owner
Role
Claude Code-style programming assistant that organizes sessions, tools, plan/exec, build work and context compaction into a runnable coding harness.
Actions
  • Owned plugin selection, coding standards and the overall architecture.
  • Built the session lifecycle and a streaming TUI/CLI interaction layer.
  • Implemented file ops, code search, script execution, LSP checks and web search.
Impact
Delivered 20+ tool capabilities plus Plan / Exec, Compaction and Build sub-agents, allowing complex coding tasks to be split, executed and compacted.

Encrypted IM client

· cross-platform client core engineer
Role
Matrix-based Android, Electron and web client work covering rich text, deeplinks, navigation structure, deployment and Rust SDK maintenance.
Actions
  • Customized Matrix rich-text parsing and invite-link navigation.
  • Rebuilt the app-level deeplink dispatcher and decoupled flows through Appyx.
  • Maintained the Rust SDK and Debug / Release deployment paths.
Impact
With quality gates around AI-assisted coding, roughly 80% of business and boilerplate code was AI-generated, lifting delivery throughput about 3x.

Quantitative trading desktop

· live-trading app technical rebuild
Role
Desktop client for live quantitative trading, covering build architecture, strategy editing, data visualization, automated release and error-context governance.
Actions
  • Replaced electron-forge + webpack with electron-builder + Rspack.
  • Integrated TradingView, Monaco Editor and a GitHub Actions release flow.
  • Moved key JS modules into Rust via napi-rs.
Impact
Cut compile/package time from 18s+ to under 4s and established GitHub Release plus private CDN distribution.

Nebula low-code platform

· low-code SaaS frontend engineer
Role
Frontend and mobile migration work for an enterprise low-code platform, spanning workflow approval, maps, material persistence, runtime theming and legacy reuse.
Actions
  • Authored team collaboration standards and shipped an internal CLI.
  • Moved large material data from Web Storage to IndexedDB and migrated CSS Modules to CSS-in-JS.
  • Reused legacy flows through Module Federation to shorten the migration cycle.
Impact
Supported private deployment delivery that contributed to a 1M RMB-tier project while reducing merge conflict, review and migration overhead.

AI Judgment & Action

2023Constrain collaboration first

In low-code work I reached for standards and CLI tooling before more screens; complex frontend teams usually bottleneck at ownership boundaries.

2024Client UX starts at build time

The quant desktop rebuild prioritized build and release repeatability because live-trading reliability depends on each shippable loop.

2025Agents need observability

Approvals, budgets, retrieval and fallback belong inside the harness, otherwise model capability stays trapped in unreviewable prompt debugging.

Core Skills

Agent Skills/tools
Wrap domain actions with Skills / MCP / Tool Calling, then add approval edges, structured output, streaming feedback and failure recovery.
Harness/runtime
Session lifecycle, Plan / Exec, hooks, compaction, permission modes and sandbox execution for moving agents from demo to runnable systems.
Memory/context
Memory files, graph context, token budgets, prompt caching and wasTruncated markers to manage input quality and reasoning cost.
RAG/retrieval
Chunking, embeddings, FTS, title matching, tag indexes, hybrid recall, LLM reranking and citation traceability.
Product/engineering
TypeScript, React, Svelte, Electron, Tauri, Expo, Hono, oRPC, PostgreSQL, Rust and Docker across frontend, client and server surfaces.

Education

Sichuan University Jinjiang College B.Eng. · Software Engineering · system capability built through shipping and open-source practice