Inbox Automator
Sort leads from email
new inquiryLeads
pricing questionLeads
demo requestLeads
partnershipPartners
newsletter replyNurture
your ideas become tools you can actually use.
start with an everyday problem and turn it into a small working system: tools, automations, trackers, and agents that quietly make your week easier. the cards below are examples of the kind of tools students build in the dojo — not promptdojo features.
Calendar Tool
Reschedule my week
MON
TUE
WED
THU
FRI
9
team meeting
focus time
10
client call
conflict
11
project review
lunch
12
Job Match Agent
Find + tailor roles
Lead Tracker
Follow up & close more
New
Ava
Ben
Contacted
Maya
Liam
Qualified
Noah
Proposal
Zoe
Won
Kai
Build Log
Document progress & own it
idea
→
plan
→
tool
→
shipped
Progress100%
the builder loop
spot the repeat
name the task you keep doing by hand, with the messy details included.
shape the tool
describe a small tool in plain English, then let ai draft the first version.
test and change it
run it, inspect what happened, and understand enough to make the next change.
the bugs ai shipped this week
a weekly post-mortem of what cursor and claude got wrong
one email a week. new chapters, the bugs ai shipped, the threads. unsubscribe in one click.
start here: 48 live chapters, picked highlights below.
from worker to builder
you are not here to become a programmer overnight. you are here to stop doing repeated work by hand. learn the builder loop, turn old workplace deliverables into interactive site artifacts, and build your first reusable tool before syntax appears.
functions
ai writes functions constantly, and can silently forget the `return` line. learn to spot the missing return on sight.
tracebacks
when python crashes, it tells you exactly what happened and where. most non-engineers panic at the wall of text. you're going to learn to read it.
llm apis
every ai feature you ship eventually calls a model api. learn the messages pattern, how to read the response, and the four lines ai writes every single time.
agent loops
an agent isn't magic. it's a while loop. learn the actual cycle claude code, cursor, and every other agent uses: model returns tool_use, you run the tool, you send the result back, repeat until end_turn.
capstone
wire it all together. the prompt, the call, the validation, the trace, the eval, the MCP tool. less a tutorial demo, more the smallest end-to-end llm feature you could ship to a real user. (retrieval and prompt-cache cost work live in chapters 22-23 — extend the capstone with them when you scale past the demo input set.)
for teams
your team is already using ai at work. most of them need a calmer path from user to builder.
promptdojo for teams gives your whole organization the builder-literacy spine, domain electives, and accountability a company actually needs.
accountability
assign paths by role. see who started, who's moving, who's stuck.
completion data
progress visibility and completion receipts, not a pile of unused logins.
built for the role
each team gets role-fit electives, artifact rubrics, and cohort pacing.
team plans help keep the free path open while funding deeper lessons, better rubrics, and the team visibility companies actually need.