Practice Observations

Observations of specific engineering use cases, encountered problems, and reported practices extracted from the evidence corpus.

18Evidence
18Assessed
0Pending
39Observations
100%Coverage

Assessment coverage measures evidence records explicitly assessed for practice observations. Assessed evidence may legitimately contain zero observations.

39 practice observations

CompanySpecific use case being solvedProblem encounteredReported practiceSelection condition
CursorTurn completed agent work into reusable improvements for future workflows.Learnings from completed tasks disappear unless they are reviewed and encoded into durable workflow artifacts.The Reflect skill runs three parallel reviewers, synthesizes durable learnings, checks whether they should be encoded structurally, and requires approval before skill edits.learningverification
CursorKeep verification evidence valid as agent-authored pull requests change.A verification verdict can become stale when the pull-request head changes.pstack records verification verdicts against a pull-request number and head SHA and voids the verdict when the head SHA changes.verification
CursorCoordinate multi-day programs containing many stacked pull requests and subagents.Parallel work needs explicit ownership, bounded context transfer, durable state, and independent verification.pstack defines coordinator, optional sub-coordinator, worker, and verifier roles; structured state files; queue events; and worker briefs.contextcoordinationverification
CursorChoose whether a task should use multi-agent orchestration or a plain agent.Coordination ceremony can cost more than it saves on work small enough for one agent.The Orchestrate playbook says not to orchestrate when one agent can finish inside the task budget and uses a task-scale threshold for orchestration.coordinationeconomics
Teresa TorresDetermine whether a change to an AI workflow actually improves its behavior.Anecdotal testing cannot reliably distinguish an improvement from a regression.Establish a baseline, change prompt/context/model/decomposition/orchestration, rerun the same inputs, apply evals, and compare scores.learningverification
Teresa TorresTurn failures observed in real AI usage into regression protection.Production failures remain isolated incidents unless they become reusable evaluation criteria.Review traces, log and categorize recurring mistakes, and turn those failure categories into eval candidates.learningobservabilityverification
Teresa TorresRun judgment-based evaluation without paying its cost for every case.LLM-as-a-Judge evaluations are more expensive than deterministic assertions.Use a cheap code assertion first and send only threshold-crossing cases to an LLM judge.economicsverification
InfobipContinue or reconstruct engineering work across agent sessions.Important state disappears when it exists only in conversational history.The workflow externalizes durable state into Git, task state, logs, and other artifacts.contextlearning
InfobipCarry a coding task from research through planning, task definition, and implementation.One growing context across the workflow becomes noisy and allows upstream errors to compound into implementation.Infobip structures work into four phases and repeatedly writes, selects, compresses, and isolates context between phases.context
InfobipDelegate implementation to fresh coding-agent sessions with sufficient task context.Fresh sessions need goals, dependencies, relevant code paths, success criteria, and validation methods without relying on conversational history.Research and planning produce validated artifacts, and task definitions carry goals, dependencies, code paths, acceptance criteria, and validation methods.contextverification
UberReduce the cost of high-volume agentic engineering work.Using an expensive primary model for every bounded subtask makes scaled execution more costly.A primary model decomposes and evaluates work while lower-cost subagents execute bounded tasks.coordinationeconomics
UberDetermine whether agent automation is economically efficient.Token or request spend alone does not show how much useful engineering work was delivered.Uber tracks outcome-denominated cost together with workload-specific quality signals and delivered volume.economicsverification
UberFind expensive behavioral patterns in live agent sessions.Repeated unnecessary tool use and other poor session behaviors can silently consume compute.Uber uses live cost counters and a session-analysis dashboard that identifies 16 anti-pattern classes with financial impact and targeted remediation.economicslearningobservability
UberChoose models for specific managed software-engineering agent workloads.General model benchmarks do not establish the best quality, reliability, and economics for a particular production workload.Uber builds benchmarks from each managed agent's real work and evaluates cost per completed task, output quality, and reliability.economicsverification
CursorIntegrate changes produced simultaneously by many agents.Conventional merge behavior accumulated more than 70,000 conflicts in an earlier run.Cursor uses neutral third-party agents for merge conflicts and a purpose-built version-control system at higher commit throughput.coordinationexecution
CursorCoordinate hundreds of agents building a substantial software system concurrently.Homogeneous agents make conflicting architectural decisions and spend context on both global planning and local implementation.Cursor separates planner agents that decompose and delegate goals from worker agents that execute bounded pieces.contextcoordination
CursorKeep independently produced implementation decisions coherent across a swarm.Workers can make locally reasonable but globally incompatible design decisions.Cursor uses reconciler agents to resolve conflicting design decisions.coordination
CursorReview large volumes of concurrently agent-produced code.A single review mechanism can become a verification bottleneck as swarm output grows.Cursor uses stacked review agents with different review lenses.coordinationverification
SpotifyCoordinate agent-generated migrations across thousands of repositories while directing scarce human attention.At fleet scale, teams need to know which changes were created or merged and which require human intervention.Fleetshift schedules and orchestrates Honk changes and tracks migration progress, pull-request state, and changes needing human attention.coordinationobservability
SpotifyRun many background coding-agent sessions with controlled execution and verification.Autonomous sessions need an execution environment with trusted tools and a reliable quality gate.Spotify runs Honk sessions in Kubernetes with trusted tools and CI verification.executionverification
SpotifyGive coding agents organizational context about software components before and during engineering work.Agents need component ownership, documentation, and responsible-team information that is not necessarily present in source files.Spotify exposes Backstage's software catalog to agents through MCPs and command-line tools.context
Google CloudRun agent jobs that continue for hours or days and survive infrastructure or human interruptions.A long-running agent cannot depend on one process or session remaining alive for the duration of the work.Google Agent Executor uses durable event logs and snapshots to support execution, resumption, and distributed deployment.executionobservability
OpenAIRun more concurrent Codex coding tasks than an engineer can comfortably supervise as separate sessions.Engineers lost track of work and debugged stalled agents beyond roughly three to five simultaneous sessions.Symphony moves task assignment and workspace lifecycle into an always-on orchestrator where open tasks receive agents in isolated workspaces and humans review outcomes.coordinationexecutionobservabilityverification
CursorExecute multiple parts of an engineering task concurrently.Parallel agent work needs decomposition, isolation, and dependency-aware composition to avoid interfering changes.Cursor Multitask decomposes work into asynchronous subagents, uses worktrees to isolate concurrent changes, and parallel plans to preserve task dependencies.coordinationexecution
SpotifyFind concrete source locations that require changes during a fleet-wide migration.Knowing the downstream consumer does not identify the actual repository usages that need modification.Spotify uses Codesearch queries to locate migration targets across its GitHub Enterprise landscape.context
SpotifyIdentify repositories affected by a downstream dataset migration.The migration system must know which repositories consume the changed dataset before an agent can modify them.Spotify uses Backstage endpoint lineage to identify downstream consumers.context
SpotifyApply a dataset migration across thousands of downstream consumers.Repository-scale changes need coordinated scheduling and pull-request execution across a large fleet.Spotify combines Honk, Backstage, Codesearch, and Fleet Management to target and orchestrate the migration.coordinationexecution
Gloaguen et al.Provide coding agents repository-specific instructions, workflow guidance, and tool information.Agents need repository-specific knowledge, but extra context can be redundant and increase exploration and inference cost without improving task resolution.The evaluated CTXbench repositories use developer-committed repository context files that agents read and follow during coding tasks.contexteconomics
Lulla et al.Provide coding agents repository-specific guidance while they execute pull-request tasks.Agents otherwise need to infer repository-specific instructions during execution, which can increase completion time and generated output.The evaluated repositories provide a version-controlled root AGENTS.md file as repository-level context for the coding agent.contexteconomics
SpotifyRun background coding agents with predictable behavior.Greater execution flexibility increases unpredictable behavior.Spotify constrains permissions, available binaries, and execution through sandboxing and surrounding infrastructure.execution
SpotifyDetermine whether an autonomously generated change is ready to become a pull request.Agent completion does not establish that the generated code works or satisfies the task.Spotify selects independent deterministic verifiers from repository contents and requires relevant verification before a pull request can be opened, then applies an LLM judge to the diff.verification
SpotifyAutomatically repair an agent-generated change that fails quality evaluation.A verifier or judge veto would otherwise leave failed work for a human to recover.Judge vetoes are fed back into the coding-agent loop, and Spotify reports that the agent course-corrects about half of vetoed cases.learningverification
BunUse a coding agent to fix bugs in the Bun repository.An agent-authored fix needs evidence that it resolves the bug rather than merely changing code.Bun's Claude Code bot opens pull requests with tests that fail against the earlier system-installed Bun and pass against the fixed debug build, then responds to review comments.executionverification
SpotifyGive different background coding agents instructions they can execute effectively.A single prompt style did not work equally well across agent architectures.Spotify tailored prompt structure to the agent, using strict step-by-step prompts for its homegrown agent and outcome-oriented prompts for Claude Code.context
SpotifyMake autonomous background coding runs more predictable.Additional dynamically fetched context and tools increase dimensions of unpredictability.Spotify limits tools and hooks, constrains Git and Bash operations, and exposes standardized verification.contextexecutionverification
SpotifyImprove the likelihood that a background coding task ends in a usable change.Broad tasks without concrete success criteria are harder for agents to complete predictably.Spotify uses tests, concrete examples, preconditions, and smaller task scope as verifiable end states.verification
SpotifyExecute software migrations across a large repository fleet with a background coding agent.Deterministic transformation declarations do not cover every migration, while repository targeting, pull-request lifecycle, review, and production merging still need coordinated infrastructure.Spotify retained Fleet Management for repository targeting and pull-request lifecycle while replacing transformation declarations with natural-language instructions executed by a coding agent.coordinationexecution
SpotifyTurn developer requests from Slack or GitHub into background coding work.The background coding agent needs sufficient task information before it can independently produce a pull request.An interactive agent gathers task information and hands a resulting prompt to the background coding agent.contextcoordination
SpotifyOperate background coding agents predictably while agent and model components evolve.Agent execution needs formatting, linting, diff evaluation, logs, traces, and the ability to change agent or model components without rebuilding the surrounding workflow.Spotify built a pluggable CLI harness with MCP-based formatting and linting, LLM-as-judge diff evaluation, GCP logs, MLflow traces, and swappable agents and models.executionobservabilityverification