Draft alt text from the image’s purpose, not everything AI can name
Choose informative, functional or decorative treatment, write the needed meaning and verify it in the page’s actual context.
W3C WAI — Alt Decision Tree
LA24X / AI
Practical guides to using AI tools Page 2
Understand AI tools, check their output and build practical workflows with original sources and clear examples.
Search this section ↗Topics & guides
96 topics in this section.
Turn an AI research answer into a claim-and-evidence record
List consequential claims, attach original sources and decide which statements are verified, qualified or removed before publication.
Google Search Central — People-first Content
Write an AI prompt with an answer you can check
Specify the task, evidence and output, then test the result against concrete requirements rather than asking for “the best answer.”
OpenAI — Prompt engineering
Separate application instructions from user text in an AI request
Use the API’s supported instruction roles, keep quoted documents as data and test conflicting input before shipping an assistant.
OpenAI — Prompt engineering
Get structured AI JSON and validate what the numbers mean
Define a supported schema, handle refusals and incomplete output, then check business rules beyond successful JSON parsing.
OpenAI — Structured outputs
Function calling: the model proposes, your application authorizes
Design narrow tools, validate arguments and permissions, execute the allowed action and return its real result.
OpenAI — Function calling
Limit an AI agent’s permissions before giving it tools
Separate reading from writing, restrict accounts and destinations and require a clear authorization path for consequential actions.
docs.anthropic.com
Answer from documents with RAG without treating retrieval as proof
Retrieve relevant permitted passages, attach source references and allow the answer to say when the documents do not support a claim.
OpenAI — Retrieval
Use embeddings for similarity search without confusing similarity with truth
Compare semantic retrieval with keyword search, preserve document permissions and evaluate whether the relevant evidence is returned.
OpenAI — Embeddings
Split documents for AI without cutting the answer away from its conditions
Keep headings, clauses and table context together, then test whether a retrieved chunk can answer the question on its own.
OpenAI — Retrieval and chunking
Make AI citations point to evidence, not just a source name
Preserve source IDs and page references, attach citations to individual claims and verify that the cited passage actually supports them.
OpenAI — Retrieval
Use prompt caching for repeated context and verify the cache hit
Keep reusable material stable, follow the selected model’s caching controls and check usage instead of assuming every repeat is discounted.
OpenAI — Prompt caching
Use Batch API for work that can wait, not an interactive response
Prepare independent tasks with stable identifiers, track job status and recover partial failures without resubmitting successful items.
OpenAI — Batch API
Stream AI responses without treating partial text as a final answer
Handle documented stream events, show an unfinished state and wait for completion before parsing or acting on the result.
OpenAI — Streaming responses
Find the AI latency bottleneck before changing models
Measure queueing, retrieval, first output and completion separately, then reduce the stage that is actually delaying the task.
OpenAI — Latency optimization
Evaluate an AI change with real tasks and visible failure criteria
Keep a representative test set, define what counts as success and compare a new prompt or model without changing the test at the same time.
OpenAI — Evals
Test an AI agent’s failures before connecting real accounts
Use harmless fixtures for tool timeouts, conflicting evidence and denied actions, then verify that the application stops without inventing success.
OpenAI — Safety best practices
Protect an AI API key and bound the requests that can spend it
Keep the provider key server-side, authorize users and limit request size, model access and usage before exposing an AI feature.
platform.openai.com