LLM Tools for Coding Automation

Represent token data as vectors and identify the shapes of tensors used in a simple language model.

Calculate dot products and cosine similarity for small vectors.

Apply a matrix transformation to a vector and interpret the resulting dimensions.

Convert a short list of scores into probabilities using softmax.

Calculate mean cross-entropy loss for a toy next-token sequence.

Tokenize sample code and prose and compare how tokenization affects sequence length.

Explain how learned token and positional representations encode a model's input.

Calculate scaled dot-product attention for a small set of query, key, and value vectors.

Apply a causal attention mask to prevent access to future tokens.

Explain how multiple attention heads can capture different token relationships.

Trace information through normalization, residual connections, attention, and the MLP in a decoder block.

Explain how autoregressive generation uses the context window and key-value cache.

Construct next-token training examples from a short sequence of tokens.

Describe how mini-batch gradient descent uses sequence loss to update model parameters.

Distinguish pretraining, continued pretraining, and supervised instruction tuning.

Explain how preference optimization changes model behavior after instruction tuning.

Diagnose common hallucinations and reasoning failures from the model's training objective and available context.

Construct system, user, and assistant messages for a chat-completion request.

Write a prompt that separates instructions, supplied context, examples, and requested output.

Request structured output and validate it against a typed schema.

Implement a tool-calling loop that validates arguments and returns tool results to the model.

Control context growth through selection, truncation, and summarization.

Handle API timeouts, rate limits, retries, and duplicate requests safely.

Define an acceptance rubric for an LLM-assisted coding task.

Build a representative evaluation set from successful, ambiguous, and failure cases.

Implement deterministic validation gates for structured outputs, cited repository paths, and generated code.

Identify prompt-injection and data-exfiltration paths in a tool-enabled workflow.

Enforce least-privilege tool access and human approval for consequential actions.

Choose between RAG, long-context prompting, and model adaptation for a given knowledge task.

Design chunk boundaries and overlap for technical documents.

Create and query an embedding-based vector index.

Combine lexical and vector search for hybrid retrieval.

Generate an answer that is grounded in retrieved evidence and includes source citations.

Measure retrieval recall using a labeled set of questions and relevant passages.

Inventory the source, build, test, documentation, and configuration artifacts in a C++, C, or Python repository.

Extract symbols and structural boundaries from representative C, C++, and Python files using parser-based tools.

Create code-aware chunks that preserve symbol identity and file location.

Index source code, documentation, and build metadata with consistent provenance.

Answer codebase architecture questions using retrieved evidence and file-level citations.

Explain the roles of MCP hosts, clients, servers, tools, resources, and prompts.

Define unambiguous JSON schemas for MCP tool inputs and outputs.

Expose a local code-search or build-analysis command as an MCP tool in Python.

Connect an MCP server to a compatible coding host and verify a complete request lifecycle.

Restrict MCP filesystem, process, network, and credential access using explicit boundaries.

Prototype an evidence-backed workflow for orienting a developer in an unfamiliar repository.

Prototype a workflow that proposes focused GoogleTest or pytest unit tests from source and existing test patterns.

Prototype a workflow that drafts API or module documentation from code and verified repository evidence.

Prototype a workflow that reviews a patch against repository conventions and reports prioritized findings.

Prototype a workflow that classifies and enriches incoming issues with labels, evidence, and follow-up questions.

Prototype a workflow that extracts root-cause candidates and next actions from compiler, linker, test, and CI logs.

Define users, scope, acceptance criteria, and safety boundaries for a repository triage assistant.

Design the assistant's components and data flow across LLM APIs, RAG, MCP tools, and human approvals.

Combine classification, retrieved evidence, likely causes, and recommended next actions into a triage pipeline.

Build an evaluation suite covering normal cases, ambiguous inputs, prompt injection, and tool failures.

Package the assistant with configuration, audit logging, usage documentation, and a reproducible launch command.