Search Results
Search Results
Query: agents
Found 33 results
-
AGENTS
_private/qwestly-private-docs/SOC2/AGENTS.md# AGENTS.md โ SOC2 Compliance Documentation ## Context This directโฆ -
openai-harness-engineering-summary
articles/openai-harness-engineering-summary.mdโฆts, CI, docs, observability, tooling โ was written by Codex agents, not humans. The practice of designing the environment agenโฆ -
linkedin-and-resume-grader-tech-design
_private/qwestly-docs/Features/plan/linkedin-and-resume-grader-tech-design.mdโฆYSTEM_PROMPT`) Current flow description (lines 220-226 of `agents/prompts.py`): ``` 1. Introduce yourself briefly 2. Ask forโฆ -
unauthenticated-agent-onboarding-tech-design
_private/qwestly-docs/Features/plan/unauthenticated-agent-onboarding-tech-design.mdโฆnly a ~20-line subclass โ no existing code is touched. ``` agents/ โโโ prompts.py โ ORCHESTRATOR_SYSTEM_PROMPTโฆ -
architecture-overview
_private/qwestly-docs/Features/qwestly-agent/architecture-overview.mdโฆser request, figures out intent, and dispatches work to sub-agents or tool calls. No framework-specific opinions here โ just tโฆ -
bonus-topics
_private/qwestly-docs/Features/qwestly-agent/bonus-topics.mdโฆroduction observability. --- ## 1. Prompt Engineering for Agents This is the single most important skill in building agentiโฆ -
deployment-options
_private/qwestly-docs/Features/qwestly-agent/deployment-options.mdโฆs** | 10 | 100 (soft) | Custom | **The hard constraint for agents is function timeout.** An agent loop with 2-3 tool calls aโฆ -
framework-comparison
_private/qwestly-docs/Features/qwestly-agent/framework-comparison.mdโฆe-playing, task delegation | Low | High | โญโญโญโญ | | **OpenAI Agents SDK** | Python | Single-agent tool-use, simplicity | Low |โฆ -
human-in-the-loop
_private/qwestly-docs/Features/qwestly-agent/human-in-the-loop.mdโฆs `interrupt_before` pattern: ```python graph = StateGraph(AgentState) graph.add_node("call_llm", ...) graph.add_node("executโฆ -
index
_private/qwestly-docs/Features/qwestly-agent/index.mdโฆtic frameworks in 2026 โ LangGraph, CrewAI, AutoGen, OpenAI Agents SDK, Pydantic AI, Semantic Kernel, Dify, and more. Trade-ofโฆ -
profile-edit-tool
_private/qwestly-docs/Features/qwestly-agent/profile-edit-tool.mdโฆt-side. ### 4.3 Orchestrator Prompt The system prompt in `agents/orchestrator.py` describes all tools and instructs the LLMโฆ -
qwestly-agent-orchestration-plan
_private/qwestly-docs/Features/qwestly-agent/qwestly-agent-orchestration-plan.mdโฆtart with a single orchestrator + tools, add specialist sub-agents as the prompt grows too complex. --- ## System Architectuโฆ -
rag-and-tools-patterns
_private/qwestly-docs/Features/qwestly-agent/rag-and-tools-patterns.mdโฆritical design decision. Mixing them up leads to unreliable agents. ### Use a TOOL when: - **The data is structured**. Userโฆ -
testing-agentic-systems
_private/qwestly-docs/Features/qwestly-agent/testing-agentic-systems.mdโฆpython assert add(2, 2) == 4 # Always passes, forever ``` Agents are non-deterministic: ```python result = await agent.run(โฆ -
adam
_private/qwestly-private-docs/HR/Personnel/adam/adam.mdโฆing prototype; now collaborating on bite-size interview sub-agents - **David** โ brought in as intern Jul 2025, converted to fโฆ -
dominick
_private/qwestly-private-docs/HR/Personnel/dominick.mdโฆ06** using DeepSeek Flash - **Bite-size interview** โ 5 sub-agents for different value propositions - **Centralized prompt exeโฆ -
vela
_private/qwestly-private-docs/HR/Personnel/vela/vela.mdโฆs for production prompts completed; bite-size interview sub-agents; document generation system | | Present | Qwestly agent intโฆ -
CLAUDE
_private/qwestly-private-docs/SOC2/CLAUDE.mdSee [AGENTS.md](AGENTS.md). -
deepseek
AI/deepseek.mdโฆde Code tools (file read/edit/write, bash, glob, grep, git, agents, cron, skills, etc.) are provided by the **Claude Code harnโฆ -
oh-my-pi
AI/oh-my-pi.mdโฆ` (user) | | Claude | 80 | `.claude/` directories | | Codex/Agents | 70 | `.codex/` directories | | Gemini | 60 | `.gemini/` dโฆ -
pi-coding-agent
AI/pi-coding-agent.mdโฆty packages that follow the [Agent Skills standard](https://agentskills.io). They're simpler than MCP โ a skill is just a foldโฆ -
skills
AI/skills.mdโฆview-toolkit/` - **Mechanism**: Launches specialized review agents (code-reviewer, silent-failure-hunter, comment-analyzer, prโฆ -
workspace-harness
AI/workspace-harness.mdโฆlding within a connected set of repositories, leveraging AI agents with cross-repo context. ## Philosophy A workspace harnesโฆ -
founders-coding-again-summary
articles/founders-coding-again-summary.mdโฆdically different outputs. A leader who can't read the code agents produce is flying blind. - **Judgment compounds.** When AIโฆ -
vercel
documents/dev/vercel.mdโฆlows is a fully managed platform for durable functions / AI agents (JS, TS, Python). Mark a function as a workflow by placingโฆ -
bring-your-own-agent-acp-portable-editors
posts/ideas/bring-your-own-agent-acp-portable-editors.mdโฆโ open standard from Zed/Anthropic/Cursor, like LSP for AI agents - **Avante.nvim** โ Neovim plugin that spawns any ACP agentโฆ -
engineering-harness-ai-bottleneck-approval
posts/ideas/engineering-harness-ai-bottleneck-approval.mdโฆssuming humans would do most of the work. Then we built AI agents that could read and write our docs, search our meetings, maโฆ -
AI-powered-development
presentations/AI-powered-development.mdโฆtly Engineering Learning Series ## AI-Powered Code Editing, Agents, and Custom Toolchains > Engineering Excellence > 2026 --โฆ -
agent-conversations-schema-redesign
qwestly-workspace/docs/agent-conversations-schema-redesign.mdโฆ`is_system`) 3. **Update SSE streaming** in `qwestly-agent/agents/base.py`: - Read `part.tool_call_id` from Pydantic AI'sโฆ -
mac-studio
services/mac-studio.mdโฆtop is via launchd: ```bash launchctl load ~/Library/LaunchAgents/com.user.ttyd.plist # start launchctl unload ~/Libraryโฆ -
openclaw
services/openclaw.mdโฆnfig โโโ workspace/ # Working directory โ โโโ AGENTS.md # Agent behavior guide โ โโโ SOUL.mdโฆ -
agent-drafts-linkedin-suggestion
_private/qwestly-docs/Features/qwestly-agent/agent-drafts-linkedin-suggestion.md# Agent Drafts & LinkedIn Profile Suggestion ## Overview The qwestly-agent can generate LinkedIn About sections using the same LangSmith prompt as the candidate app's admin LinkedIn Suggestions page -
Internship Agreement - Cohen Russell
_private/qwestly-private-docs/HR/Personnel/cohen/Internship Agreement - Cohen Russell.md# QWESTLY INTERNSHIP AGREEMENT **This Agreement** is between Qwestly, Inc. ("Qwestly" or "the Company") and Cohen Russell ("Intern") and his parent/guardian ("Parent/Guardian"). ## **1. Internship T