GO TO A SECTION

↑ ↓ to navigate · Enter to openExplore all sections →
FDEInterviews logo
← RAG & Agent System Design / 43
hardAnthropicSierraCognition

An agentic loop runs forever on long-horizon tasks. Propose an algorithmic change to stop the looping and evaluate it offline.

Hard budgets stop the bleeding; they don't fix the cause. The real fix is progress tracking plus semantic loop detection plus a planning layer that commits to a plan instead of re-deciding every step, validated on a fixed trajectory set offline before it ships.

Updated Aug 2026 · Grounded in real Forward Deployed Engineer interview loops and written to a senior-engineer editorial bar.

Hard budgets stop the bleeding; they don't fix the cause. The real fix is progress tracking plus semantic loop detection plus a planning layer that commits to a plan instead of re-deciding every step, validated on a fixed trajectory set offline before it ships.

20 answers per topic instead of 10, plus saved progress and bookmarks · no cardor unlock all 548 remaining answers · ₹2,000 / $25

Every answer, concept and course, every paper breakdown, all published video lessons, hands-on FDE Lab missions, Premium PDF guides and companion files, the full practice-test bank and work-sample downloads. Referral Premium excludes guide PDFs and their companion files.

6 months · One payment · No auto-renewal

Study alongside free video lessons.

Keep practising

Next in this trackDesign a Graph-RAG pipeline that turns a question into Cypher, runs it, and heals its own broken queries.PremiumNext in this trackBuild a simulation harness that evaluates a non-deterministic researcher-writer multi-agent system under injected faults.PremiumNext in this trackDesign a Planner-Coder-Reviewer-Tester system that turns a Jira ticket into tested code and fixes its own bugs.Premium
FEDITOR'S NOTE

The screen is whether the candidate gives a real algorithmic change (progress/state tracking, semantic loop detection, plan-then-execute or tree search) rather than only a step cap, AND can describe offline evaluation on a fixed task set with trajectory-level metrics. The strong move is layering a cheap hard budget as a backstop under a smarter progress-based stop, plus a frozen replay/trajectory eval harness. The reserved follow-up: 'a step limit just truncates the task, how do you stop WITHOUT failing the task' and 'what do you measure offline besides final success.'

DISCUSSION · 0

No comments yet — be the first to share your approach.