£299 programme

Mai Studies Original · Computing

Build an AI Agent Identity and Permissions Platform

An extended build-along programme. Software agents now act on their own, yet most of them run on a shared secret key with no record of who asked for what, no limit on what they may spend and no way to prove afterwards what was decided. You build the missing control layer yourself, one stage at a time, with coding challenges marked instantly in the page and a stage deliverable marked against a published rubric. Every stage adds a working piece: a registry of provable agent identities, scoped capability grants, delegation chains that only ever narrow, spend and rate budgets that refuse politely, a tamper-evident log of every decision, and a final runtime gateway that puts all of it in front of a live request. This is a Mai Studies record of study, not a regulated qualification.

12 weeks 90 guided hours Advanced

No account needed to buy. Pay with your card and we create your student account from the email you enter, with this programme ready inside it for twelve months.

Build an AI Agent Identity and Permissions Platform course artwork

What you will achieve

Give every agent an identity that can be proved and revoked
Express permissions as narrow, time-limited capability grants
Build delegation chains that can only narrow, never widen
Hold agents to spend and rate budgets that refuse safely
Keep a tamper-evident record of every decision taken
Ship a runtime gateway that allows or refuses a live agent request

Entry guidance

— Comfortable writing JavaScript functions
— Willing to build and test your own code each stage

Original Mai Studies learning material. This is a professional completion programme, not a regulated qualification or university accreditation.

Programme syllabus

6 applied modules

Lessons: 12
Assessed tasks: 6
Practice questions: 72
Timed mock papers: 2

01

Stage 1: An identity an agent can prove

Replace the shared secret with a registry of agent identities, each with its own key pair, fingerprint and revocation state.

2 lessons · 12 practice questions · 1 assessed task

1. Notes: why agents need a provable name35 min study · 3 learning objectives · practical activity
Explain the weakness of a shared agent key
2. Build: the agent registry35 min study · 3 learning objectives · practical activity
Write a stable fingerprint for an agent record

Stage 1 deliverable: the agent registry — marked out of 100, pass at 80%

02

Stage 2: Scoped capability grants

Express permission as a narrow grant: one action, one resource, one expiry, instead of a blanket key that can do anything.

2 lessons · 12 practice questions · 1 assessed task

1. Notes: permission as a narrow grant37 min study · 3 learning objectives · practical activity
Describe a capability grant and its parts
2. Build: the grant checker36 min study · 3 learning objectives · practical activity
Match an action and resource against a grant

Stage 2 deliverable: the grant checker — marked out of 100, pass at 80%

03

Stage 3: Delegation that only narrows

Let an agent act on behalf of a person or another agent, with a chain that can attenuate rights but never widen them.

2 lessons · 12 practice questions · 1 assessed task

1. Notes: delegation that only narrows37 min study · 3 learning objectives · practical activity
Explain on-behalf-of delegation
2. Build: the chain validator35 min study · 3 learning objectives · practical activity
Validate each link against the one above

Stage 3 deliverable: the delegation chain — marked out of 100, pass at 80%

04

Stage 4: Spend and rate budgets

Hold every agent to a budget of money and calls, refuse politely at the limit and make the refusal auditable.

2 lessons · 12 practice questions · 1 assessed task

1. Notes: budgets that refuse politely37 min study · 3 learning objectives · practical activity
Separate money budgets from rate budgets
2. Build: the budget keeper34 min study · 3 learning objectives · practical activity
Check and deduct in one step

Stage 4 deliverable: the budget keeper — marked out of 100, pass at 80%

05

Stage 5: A tamper-evident decision log

Chain every allow and refuse decision by hash so a later edit is detectable by anyone holding the log.

2 lessons · 12 practice questions · 1 assessed task

1. Notes: a log nobody can quietly edit37 min study · 3 learning objectives · practical activity
Explain hash chaining in plain terms
2. Build: the decision log36 min study · 3 learning objectives · practical activity
Append an entry linked to the previous one

Stage 5 deliverable: the decision log — marked out of 100, pass at 80%

06

Stage 6 final build: the runtime policy gateway

Put the whole control layer in front of a live request and return a clear allow or refuse with the reason and the evidence.

2 lessons · 12 practice questions · 1 assessed task

1. Notes: putting the gateway in front of a live request37 min study · 3 learning objectives · practical activity
Order the checks correctly
2. Build: the gateway and the handover35 min study · 3 learning objectives · practical activity
Combine every control into one decision

Stage 6 deliverable: the gateway and handover — marked out of 100, pass at 80%

Timed mock papers

Build an AI Agent Identity and Permissions Platform: timed mock paper 1 — 180 minutes, 30 objective questions plus written and computational tasks
Build an AI Agent Identity and Permissions Platform: timed mock paper 2 — 180 minutes, 30 objective questions plus written and computational tasks

Lesson pages, assessed tasks and mock papers open the moment you join this programme. Teaching material is studied online; the notes you write are yours to download.

What students say

No ratings yet.

Sign in as a student on this programme to leave a rating.