The End of
User Centric
Product Development
Software agent, a computer program that performs various actions continuously and autonomously on behalf of an individual or an organization.
A Generative AI Agent
is defined as an application
that tries to achieve a goal by
observing the world and acting
upon it using the tools it
has at his disposal
Ich möchte nächstes Wochenende von Berlin nach Hamburg fahren. Suche mir einen Bus bei Flixbus heraus.
DemoTime
Conversational Agents
- Chat with your documents
- Q&A, Knowledge Interactions
- User queries (like NQL) :-)
- fulfil user transactions
- Everything CoPilot, ChatGPT, ...
- Chat, Voice, Mail.
Chatbots are the Ford Model T of AI
- This is not just a faster horse.
- It is a lot more flexible and configurable
- It is faster, can carry heavier weights, more comfortable
- The actual revolution was still something else: automation
Autonomous /
Workflow Agents
- Limited User Interaction
- Event driven, Queues of Tasks
- Chains of task execution
Human in the loop
Ask and remember
How to build
an Agent
Perception & Tools
Right now:
- all documents
- all images
- all sounds
- all apis
- all databases
- all services
Soon:
- your desktop
- your phone
- robots
Strategy & Planning
- o1-preview: evaluate plans before acting
- Who taught o1 the strategies?
- Yep, we did.
- We can do this for
agents, too.
Decisions
- Did we reach our goal?
- What tool should we try next?
- Are we in a loop?
- Is the result of the tool helpful?
Memory
- Short Term Memory
- "What do i need to know
for this decision" - "What do i need to
plan my next steps" - Mostly prompt
- "What do i need to know
- Long Term Memory
- Which strategy actually worked out?
- which strategy went bad?
- Which steps were useless?
- Mostly vectordb
Reflection and Learning
The reason why Strawberry's R are not a problem anymore
-
Reflection
-
Feedback loops
-
Backtesting
-
RLHF
Flow Engineering
In Agentic AI,
user activity
is waste
expensive.
User Story Mapping?
Impact Mapping
How to capture requirements
without any users ...
Todo:
The Cognitive Architecture
-
Strategy/Planning
-
Decisions and Knowledge
-
Reflection and Learning
-
Self-Optimization / Generalisation
"As an Agent, i want
to remember working
strategies to learn."
We haven't solved this one yet.
BUT ...
You never know if you can rely on AI ...
Backtesting, Learning.
"Create a product vision for the company replacing flixbus."
"Decide which is the most important app. Provide UX and user journey concept."
"Create a prototype for this user journey."
React-Prototype after 30 seconds:
This could have
been 100 Click-
Dummies
It's not human,
some tasks need empathy.
It's just a fad.
It won't stay.
“The horse is here to stay, but the automobile is only a novelty – a fad.”
President of the Michigan Savings Bank, advising Horace Rackham (Henry Ford’s lawyer) not to invest in the Ford Motor Company, 1903
- Automatisierung der Produktion:
10.000 Fahrzeuge pro Tag
- Ein Ford Model T wurde in
93 Minuten vollständig produziert
- Die Preise konnten in 5 Jahren von
950$ auf 360$ gesenkt werden
Industrialisierung
The industrialization of
knowledge work:
elastic knowledge work
- 100 times more expensive than software
-
100 times less expensive than humans.
- If you got one agent, you got 1000, too.
- Failing 20 times before it works is still cheap.
Helpful metaphors
-
1000 smart & eager to work interns:
What should they do for you?
- If you had 100 hours instead of one
for the next task, what would you do?
Horace Rackham still invested
5.000$ in Ford stock and sold them
later for 12.5000.000$
You could use a car instead of a horse, too.
Or even scale it and travel by bus or train.
Automating Knowledge
Work
The End of user centric product development
By Johann-Peter Hartmann
The End of user centric product development
As a product owner i want to use AI so i won't get replaced by AI.
- 103