TextAI Agents
Auditable Enterprise LLM Agent Harness Architect
Reconstruct prompt-heavy enterprise LLM prototypes into a traceable, auditable, code-owned agent architecture by moving behavior into manifests, schemas, validators, and runtime gates.
Tag Collection
智能体架构 Prompt Collection
Agent design is mostly a division-of-labour and boundary problem, not a model-capability problem. At the prompt layer you must state who may call which tool, when to stop and confirm, how to roll back on failure, and where state is recorded.
Related prompts
9 prompts
TextAI Agents
A2UI Agent-to-User Interface Architect
Act as an A2UI architect who turns product requirements into secure, declarative, agent-generated UI designs using Google's A2UI open protocol, producing structured JSON contracts and component allowlists.
TextAI Agents
Quantitative Trading Agent Architect
Design an autonomous quantitative finance research agent that transforms natural-language financial questions into testable strategies, rigorous backtests, and inspectable research artifacts across equities, crypto, futures, and forex—without executing live trades—ensuring reproducibility, safety, and cross-platform interoperability.
TextAI Agents
Agents Best Practices Guide
This skill is used when designing, generating an MVP blueprint for, auditing, refactoring, or explaining an agentic harness for any domain. Covers provider-neutral agent architecture for OpenAI, Anthropic, and OpenAI-compatible APIs: agent loops, tool design, permissions, system prompts, planning, goals, context compaction, memory, skills, MCP/external connectors, observability, evals, prompt caching, agent-legible environments, feedback loops, and safety.
TextAI Agents
Self-Improving Agent Architect
Design autonomous agent systems that learn from experience, persist knowledge across sessions, and grow more capable over time without manual prompt engineering. Includes skill ecosystem, multi-platform gateway, model-agnostic layer, and safety governance.
TextAI Agents
Open Deep Research Agent Architect
Design an end-to-end open-source deep research agent system that competes with closed commercial offerings (e.g., OpenAI Deep Research). The agent must answer complex, multi-hop questions over the open web with verifiable citations, long-horizon planning, and reproducible runs. This includes data pipeline, training recipe, inference modes, tool stack, evaluation harness, deployment topology, and governance.
TextAI Agents
Elastic Context Orchestrator Design
Design a dynamic context management system for long-horizon agents that selectively preserves, compresses, rolls back, and deletes context to control growth, reduce hallucination, and improve reasoning efficiency.
TextAI Agents
Agent Memory Architect
Design memory systems for long-running agents to learn from experience, avoid repetitive mistakes, and retrieve relevant context at the right time—without token bloat or stale recollections.
TextAI Agents
Agent Harness Designer
Design a safe, debuggable, reversible, and measurable runtime environment for an agent, clarifying the model's role within a larger production system.
One agent or several?
Keep a single agent for short linear tasks. Split when you need parallelism, role isolation or independent audit trails.
How do I stop an agent misusing tools?
Whitelist the tools it may call, and require a stated reason and expected side effect before each call.
Should state live in the prompt?
Keep execution state outside; hold only the current step, confirmed facts and next action in the prompt.