00_Hackers ✌️

As an Agentic AI Engineer, you must build these projects. 1.) Async Agent Orchestrator Build: A FastAPI + asyncio event loop handling 100+ concurrent agent tasks with non-blocking tool calls and graceful error recovery. Why: `while True` loops block the main thread. Real-world agents require event-driven concurrency to survive production traffic. 2.) Dynamic Context Budget Assembler Build: A pre-flight middleware that strictly allocates tokens across system prompts, retrieved docs and tool schemas per request. Why: Context overflow is the #1 silent killer of production agents. You must budget tokens like you budget cloud spend. 3.) Strict Pydantic Tool Router Build: A tool execution engine that forces LLM outputs into strict JSON schemas and automatically retries with the error trace on validation failure. Why: Agents hallucinate API parameters. Grammar-constrained decoding and Pydantic validation turn stochastic outputs into deterministic actions. 4.) 3-Tier Memory & Eviction Engine Build: A memory system with working scratchpads, episodic session compression and semantic vector search with automated TTL eviction. Why: Infinite context causes OOM errors and hallucinations. Memory must be actively managed, scored and pruned. 5.) Self-Healing ReAct Loop Build: An agent that reads its own stack traces, parses the compiler/API error, rewrites the failing tool call and retries up to 3 times. Why: Agents that fail on the first try are useless. Agents that debug themselves are digital employees. 6.) Typed Multi-Agent Swarm Build: A LangGraph state machine where a Researcher, Coder and Reviewer agent pass strictly typed state objects, never raw text. Why: Single agents fail on complex tasks. Swarms divide and conquer but raw text handoffs cause context drift. 7.) Async HITL Slack Gate Build: A workflow that drafts a high-stakes action, serializes its state and waits 3 days for a human to click "Approve" via a Slack webhook. Why: High-stakes automation requires human accountability. Agents must know how to pause, wait, and resume cleanly. 8.) Trajectory Eval CI Gate Build: A GitHub Action that replays 100 agent trajectories and blocks the PR if the tool-call sequence deviates from the golden DAG. Why: Grading the final text output hides the fact that the agent hallucinated an API call or skipped a safety check to get there. 9.) OpenTelemetry Agent Tracer Build: Custom tracing spans capturing every LLM hop, token count, tool latency and state mutation in LangSmith or Arize. Why: You cannot debug a 14-step agent workflow if you can't replay the exact sequence of events that led to the failure. 10.) Inter-Agent Sanitization Proxy Build: Middleware that intercepts messages between agents, stripping malicious instructions to prevent cross-agent prompt injection. Why: Multi-agent systems create internal attack surfaces. Agent A can be tricked into hijacking Agent B's tools. 11.) Sandboxed Code Executor Build: A code-interpreter agent that writes and executes Python in an isolated E2B or gVisor microVM with zero internet egress. Why: Letting an LLM run `os.system()` on your host machine is a catastrophic security risk. 12.) Cost Kill-Switch Middleware Build: A router tracking loop depth and projected spend that instantly halts the agent if it exceeds $0.50, falling back to a cheaper model. Why: A runaway agent loop is an outage with an invoice. It will burn $500 in API credits before you notice. 13.) API-to-Browser Fallback Agent Build: A routing layer where if the primary REST API 404s or times out, the agent seamlessly spawns a headless browser to finish the GUI workflow. Why: The real world is messy. 80% of enterprise software has no API. Agents must adapt to broken environments. 14.) Shadow Trajectory Comparator Build: A silent 5% traffic mirror that runs a new agent topology in the background, diffing tool-call paths and costs without affecting users. Why: You cannot A/B test non-determinism safely in production without shadow mode. 15.) Public Architecture Teardown Build: 3 published deep-dives detailing your swarm topology, state-machine design, inter-agent security and cost-per-task analysis. Why: Top AI labs hire Agent Engineers based on their system design judgment not their ability to import LangChain. Systems that prove you can orchestrate, secure & scale when autonomous agents touch your stack. Most people watch tutorials. Builders ship systems. Bookmark & Repost.

If I had to pass an AI engineer technical interview in the next 24 hours, I'd practice these 25 problems. They cover 95% of the concepts. 1) Design a RAG system for 10M documents 2) Your RAG gives wrong answers. Debug it 3) Pick a chunking strategy for legal contracts 4) BM25 vs dense vs hybrid search: when to use each 5) Add a reranker and measure if it helped 6) Reduce LLM cost by 70% without hurting quality 7) Cut first-token latency for a chat app 8) Design a semantic cache with hit-rate tracking 9) Route requests between a cheap and a smart model 10) Build an agent that uses tools reliably 11) Your agent gets stuck in a loop. Fix it 12) Design memory for a long-running assistant 13) Make LLM output always valid JSON 14) Detect and reduce hallucinations 15) Build an eval suite for a customer support bot 16) LLM-as-a-judge: how to make it trustworthy 17) Block prompt injection in a tool-using agent 18) Redact PII before it hits the model 19) Fine-tune vs RAG vs prompting: pick one and defend it 20) Fine-tune a small model with LoRA on 5K examples 21) Serve an open model at scale (batching, KV cache, quantization) 22) Stream responses over SSE and handle disconnects 23) Trace every step of a multi-agent workflow 24) Roll back a bad prompt change in production 25) Design ChatGPT-style chat for 1M daily users Don't memorize answers. Practice explaining trade-offs out loud. That's what interviewers actually grade. Bookmark this. You'll need it before your next interview.