LOCKEDIN / FORWARD-DEPLOYED ENGINEERING 101
Understand it.
Then build it.
You can be an experienced engineer and still be new to agents. Start with what each thing is and how it helps a person do useful work. Explore 48 original introductions across software, agents, cloud, security and delivery. Start here without a model key; each topic connects to deeper instruction and practice.
- 101UnderstandPlain language, visual walkthrough, vocabulary
- 102Build with guidanceOriginal lessons, examples and knowledge checks
- 103Practise and explainRunnable labs, failure cases and handover
- 01Count input
- 02Reserve output
- 03Bound the task
Units of model input and output
What are tokens and token budgets?
Tokens are the units a model uses to represent content. A token can be a word, part of a word or another encoded element. Token counts affect context capacity, output limits, latency and often price. Characters, words and tokens are not interchangeable counts.
Unbounded loops and large tool responses can exhaust cost and capacity before useful work finishes.
CONNECT IT TO WHAT YOU KNOW
Start with something familiar.
Treat a request like a bounded packet with room for both the question and the answer. Filling every available space with input leaves no sensible output allowance.
Budget the complete loop: instructions, history, tool descriptions, retrieved evidence, output and repeated calls. A limit on one response is not a spending cap for an entire agent task.
Words worth knowing
- Context window
- The model's capacity for a request's context, subject to provider rules.
- Output limit
- A maximum on generated tokens for a response.
- Usage
- Provider-reported consumption for the actual request.
ONE EXAMPLE / FICTIONAL CASE
Watch the work take shape.
Four requests each reserve 4,096 prompt tokens and up to 8,192 output tokens: 49,152 tokens of total reservation.
- 01Count input
- 02Reserve output
- 03Bound the task
Count input
Use the target model's tokenizer or documented counting method; do not use a universal words-to-tokens rule.
An input estimateFROM RECOGNITION TO REASONING
Calculate the reservation before moving the capacity controls.
- 01
Compute 4 × (4,096 + 8,192).
- 02
Repeat with a 1,024-token output limit.
- 03
Open the existing capacity lab and compare your result with its synthetic memory profile.
Both totals and the assumptions behind them.
Compare your reasoning when you are ready
The totals are 49,152 and 20,480 tokens. These are reservations, not measured usage or a hardware benchmark. Model architecture and cache representation also determine memory.
Keep notes in your own working copy. Moving through these cards does not record completion.
TURN THE IDEA INTO USEFUL WORK
You can now go deeper.
Budget the complete loop: instructions, history, tool descriptions, retrieved evidence, output and repeated calls. A limit on one response is not a spending cap for an entire agent task.
Academy lessons use your existing training access. Free guides stay open.