Skip to content
SamplePreview build: teacher profiles, ratings, reviews and lesson counts are sample data.
Log inFind a tutor

Teacher since May 2025

Farid Haddad

Keeps LLM features fast, affordable and available as traffic grows: cost, caching, retries and observability

9

tutors built

4.5Sample

average from 19 reviews

347Sample

lessons taught by their tutors

About Farid

Most of my working life has been on platform and reliability teams, and these days I spend it on LLM features: the bills that surprise people, the 429 errors on launch day, the logs nobody can read. I teach the operational side of building with model APIs. We estimate costs before writing code, add retries that do not make outages worse, cache what can be cached, and log enough to answer why something cost so much or ran so slowly. I like numbers you can check yourself, so most lessons include a small calculation or a log we read together.

Knows about

  • token counting
  • cost control
  • prompt caching
  • rate limits and retries
  • batch processing
  • secrets management
  • latency budgets
  • logging and tracing
  • fallbacks and resilience

Tutors by Farid

9 tutors

Logging and Tracing LLM Calls

Logging and Tracing LLM Calls

Record every model call and pipeline step so you can explain cost, slowness and bad answers.IntermediateBuilding with LLM APIs4.0(3)65 lessonsSampleFarid Haddad$8Fallbacks for Provider Outages and Errors

Fallbacks for Provider Outages and Errors

Keep LLM features working through outages, overloads and slowdowns with deadlines, breakers and fallbacks.AdvancedBuilding with LLM APIs4.7(3)60 lessonsSampleFarid Haddad$11Token Counting and Cost Control

Token Counting and Cost Control

Count tokens, predict what a feature will cost and cut spending without hurting answer quality.BeginnerBuilding with LLM APIs4.3(3)57 lessonsSampleFarid Haddad$4Rate Limits, Retries and Backoff

Rate Limits, Retries and Backoff

Handle 429s and overloads gracefully with backoff, jitter, client side pacing and retries that never cause storms.IntermediateBuilding with LLM APIs4.7(3)53 lessonsSampleFarid Haddad$7Cost and Latency Budgets for LLM Features

Cost and Latency Budgets for LLM Features

Set cost and speed targets for an LLM feature, measure them honestly and trade them against quality.All levelsBuilding with LLM APIs4.5(2)52 lessonsSampleFarid Haddad$8API Key Safety and Secrets Handling

API Key Safety and Secrets Handling

Keep model API keys out of code, repos, browsers and logs, and know exactly what to do if one leaks.BeginnerBuilding with LLM APIs4.7(3)32 lessonsSampleFarid HaddadFreePrompt Caching for Lower Cost and Latency

Prompt Caching for Lower Cost and Latency

Structure prompts so repeated prefixes are cached, then measure the savings in cost and response time.IntermediateBuilding with LLM APIs4.5(2)28 lessonsSampleFarid Haddad$7Batch Jobs for Large LLM Workloads

Batch Jobs for Large LLM Workloads

Run thousands of model requests as batch jobs that are cheaper, resumable and easy to check.IntermediateBuilding with LLM APIsNewFarid Haddad$7LLM APIs on a Solo Developer Budget

LLM APIs on a Solo Developer Budget

Build and launch a side project on model APIs without a surprise bill, abuse or an overbuilt setup.All levelsBuilding with LLM APIsNewFarid Haddad$4

Recent reviews

What students said about Farid's tutors.

  • Ken T.Sample

    Advanced and dense, as advertised. The runbook lesson was short but useful.

    On Fallbacks for Provider Outages and Errors

  • Anika R.Sample

    The breakdown of where tokens go showed our examples block was bigger than everything else combined. Trimmed it and quality held on our test set.

    On Token Counting and Cost Control

  • Tobias E.Sample

    Clear explanation of why our German and Polish users cost more. Practical and not preachy.

    On Token Counting and Cost Control

  • Mohammed E.Sample

    We had a second provider wired up but had never evaluated it. Our parser broke on its output format in the first fault injection test. Found it in staging instead of production.

    On Fallbacks for Provider Outages and Errors

  • Signe L.Sample

    Circuit breaker explanation with real thresholds and probes was excellent. The point that degraded modes can beat a weaker model changed our design.

    On Fallbacks for Provider Outages and Errors

  • Daniel K.Sample

    As a product lead I appreciated budgets per active user rather than per token. The engineering parts were optional for me but still readable.

    On Cost and Latency Budgets for LLM Features