Season 1 · Episode 2

Give Your AI the Map

Context and continuity through the mining-claim story.

This lesson drops soon — check back here for the video and voiceover.

Watch & listen

Episode video — coming soon

Drop in your episode file and it plays here.

Voiceover — coming soon

Drop in your voiceover file and it plays here.

The assistant can’t know what you never said — and what it doesn’t know, it will invent confidently. This lesson is about context as decision-changing information: not your autobiography, but the facts, vocabulary, constraints, and prior decisions that change the answer. The vehicle is a real story: Chris’s mining-claim research, where precise terms and a durable project map turned months of scattered questions into one continuous project.

The problem this lesson solves

W

i

t

h

o

u

t

a

m

a

p

,

e

v

e

r

y

s

e

s

s

i

o

n

i

s

d

a

y

o

n

e

.

Y

o

u

r

e

-

t

e

a

c

h

t

h

e

p

r

o

j

e

c

t

,

r

e

-

e

x

p

l

a

i

n

t

h

e

t

e

r

m

s

,

a

n

d

w

a

t

c

h

t

h

e

a

s

s

i

s

t

a

n

t

c

o

n

f

i

d

e

n

t

l

y

m

i

x

u

p

t

h

i

n

g

s

y

o

u

t

h

o

u

g

h

t

w

e

r

e

s

e

t

t

l

e

d

—

l

i

k

e

t

r

e

a

t

i

n

g

a

p

a

t

e

n

t

e

d

c

l

a

i

m

,

a

n

u

n

p

a

t

e

n

t

e

d

c

l

a

i

m

,

a

n

d

f

e

e

l

a

n

d

a

s

i

n

t

e

r

c

h

a

n

g

e

a

b

l

e

w

h

e

n

t

h

e

y

a

r

e

l

e

g

a

l

l

y

d

i

f

f

e

r

e

n

t

t

h

i

n

g

s

.

W

o

r

s

e

,

r

e

m

e

m

b

e

r

e

d

c

o

n

t

e

x

t

g

e

t

s

m

i

s

t

a

k

e

n

f

o

r

p

r

o

o

f

:

t

h

e

a

s

s

i

s

t

a

n

t

“

r

e

m

e

m

b

e

r

s

”

l

a

s

t

m

o

n

t

h

’

s

p

r

i

c

e

o

r

r

u

l

e

a

n

d

p

r

e

s

e

n

t

s

i

t

a

s

c

u

r

r

e

n

t

f

a

c

t

.

T

h

e

p

r

o

b

l

e

m

t

h

i

s

l

e

s

s

o

n

s

o

l

v

e

s

i

s

b

u

i

l

d

i

n

g

c

o

n

t

e

x

t

o

n

c

e

,

k

e

e

p

i

n

g

i

t

c

o

r

r

e

c

t

,

a

n

d

k

n

o

w

i

n

g

w

h

e

r

e

m

e

m

o

r

y

e

n

d

s

a

n

d

v

e

r

i

f

i

c

a

t

i

o

n

b

e

g

i

n

s

.

The lesson, step by step

Define context as decision-changing information

Context is not everything about you. It is the specific information that would change the answer: the objective, the known facts, the vocabulary, the source hierarchy, the constraints, what’s already done, what’s unresolved, and the next action. If a detail wouldn’t change the output, it’s noise — leave it out.

Build the one-page project map

Write it down, once: objective, known facts, vocabulary, source hierarchy, constraints, completed work, unresolved questions, next action. One page, durable, updated when facts change. This is the document you hand the assistant at the start of a session instead of re-explaining everything out loud.

Use precise terms — they are not interchangeable

In the mining-claim story: patented claim, unpatented claim, fee land, placer claim, hard-rock mine, parcel, and BLM record are different legal and practical things. Swapping them doesn’t just sound wrong — it produces wrong candidates, wrong ownership conclusions, and wasted prospecting trips. Put the vocabulary in the map.

Demonstrate continuity across sessions

Session one: research the BLM record. Session two, weeks later: amend the search criteria — the assistant applies the new criteria to the existing map without re-teaching. Session three: plan a prospecting or camping trip using the researched record. No session starts from zero because the map carries the project.

Correct a durable fact once — explicitly

When a fact in the map turns out wrong, say so on the record: what the old understanding was, what the new evidence says, and what changed. One explicit correction beats ten quiet ones, because quiet corrections leave the old fact alive in half the project’s memory.

Separate memory from proof

Remembered context accelerates work, but current legal, travel, price, and availability facts still need fresh verification. Memory tells you where to look; it does not tell you what is true today. The lesson’s rule: trust the map for how the project works, verify the world for what the world says now.

Worked example

Three sessions, one project. First, Chris and Clingy Bear research BLM records and build the candidate table. Weeks later, Chris amends the criteria — closer to Spokane, patented claims preferred — and the assistant re-ranks the existing candidates instead of starting a new search. Later still, planning a prospecting trip: the assistant pulls the researched parcels, access constraints, and open questions straight from the map. The trip brief writes itself because the research was preserved, not re-performed.

Your takeaway

The BRAVE lens

Every episode runs through the BRAVE method: brief the outcome, reveal relevant context, authorize the next action, verify the evidence, and evolve the system.

Meet your hosts

Learn Muse is co-hosted by Clingy Bear, Chris Pick's AI agent, and Nugget, Aaron Kasten's AI agent.