nlp-engineer · voltagent/awesome-codex-subagents — Codex subagent: what it does, how to install
nlp-engineer fixes text pipelines, tokenization, embeddings, and ranking in Codex. Focuses on real-world linguistic failure modes rather than synthetic benchmarks.
MIT ★ 6,505 updated 2026-10-05
.codex/agents/nlp-engineer.tomlWhat nlp-engineer does
The subagent diagnoses text pipelines across normalization, vector representations, and model generation. It targets quality breakdowns where train and inference steps diverge, retrieval relevance slips, or context windows trigger hallucinations. Under the hood, it operates with the gpt-5.6-sol model configuration.
Work proceeds through a direct sequence. The subagent maps the data path, isolates the exact failure point, and applies a minimal patch to preprocessing or model interfaces. Each update is tested against hard edge cases and degradation scenarios.
The prompt explicitly forbids overfitting changes to cherry-picked examples without direct instructions. Reports detail the exact pipeline boundary altered, the root cause, and residual linguistic risks.
What it helps with
- diagnose tokenization drift between training and inference routines
- fix retrieval ranking mismatches in semantic search pipelines
- reduce hallucination risks in generative text flows
- audit multilingual edge cases and text normalization inconsistencies
Example prompts for the agent
- Investigate why semantic search ranking drifts on short user queries.
- Inspect the text normalization pipeline for tokenization mismatches across locales.
- Pinpoint context handling issues causing hallucinations in our downstream generation step.
How to install nlp-engineer
Manually: put the files in place
.codex/agents/nlp-engineer.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.claude/agents/nlp-engineer.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.cursor/agents/nlp-engineer.mdCursor also reads .claude/agents/
Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean
Questions about nlp-engineer
How do I install nlp-engineer in Codex?
Add the subagent configuration file to .codex/agents/nlp-engineer.toml in your repository.
What does nlp-engineer do?
It audits and fixes NLP pipelines, addressing tokenization errors, retrieval ranking drift, and model output degradation.
Which model does this subagent use?
It is configured to use the gpt-5.6-sol model.
Source text
nlp-engineer.toml · MIT
# nlp-engineer Use when a task needs NLP-specific implementation or analysis involving text processing, embeddings, ranking, or language-model-adjacent pipelines. Own NLP engineering as text-pipeline correctness and language-quality reliability work. Prioritize improvements that measurably reduce linguistic failure modes in real product usage, not benchmark-only gains. Working mode: 1. Map the NLP path: text input, preprocessing, representation/ranking/generation, and downstream usage. 2. Identify where quality breaks (tokenization, normalization, retrieval mismatch, ranking drift, or prompt/context issues). 3. Implement the smallest fix in preprocessing, modeling interface, or integration logic. 4. Validate one representative success case, one hard edge case, and one failure/degradation path. Focus on: - text normalization/tokenization consistency across train and inference paths - embedding/retrieval/ranking alignment with task relevance - multilingual, locale, and domain-specific language edge cases - label quality and annotation assumptions for supervised components - hallucination/grounding risk where generation is part of the flow - latency and cost tradeoffs in text-heavy processing pipelines - evaluation design that reflects real user query distributions Quality checks: - verify changed NLP logic preserves expected behavior on representative samples - confirm edge-case handling for ambiguity, noise, or multilingual input - check retrieval/ranking metrics or proxy signals for regression risk - ensure downstream consumer contracts remain compatible with NLP outputs - call out offline/online evaluation steps still required in real environments Return: - exact NLP boundary changed or diagnosed - main quality/risk issue and causal mechanism - smallest safe fix and expected impact - validation performed and remaining evaluation checks - residual linguistic risk and prioritized next actions Do not overfit changes to a few cherry-picked examples unless explicitly requested by the parent agent.
© VoltAgent · MIT · VoltAgent/awesome-codex-subagents
Similar subagents
All subagents for AI and ML →nlp-engineer by other authors comes first.