Engineering Notes
Thoughts and Ideas on AI by Muthukrishnan
Home
All posts
AI Agents
Engineering Manager
About
Resume
Tags & Stats
Tags - Engineering Notes
Tags
ai agents
90
engineering-management
57
ai
26
reinforcement learning
23
planning
19
multi-agent-systems
15
tutorial
14
llms
13
multi-agent
12
python
12
langgraph
9
llm
9
agentic-ai
8
autonomous agents
8
architecture
7
decision-making
7
reasoning
7
algorithms
6
coding
5
development
5
game theory
5
machine learning
5
tool-use
5
alignment
4
deep-research
4
orchestration
4
rag
4
research
4
testing
4
ai safety
3
coordination
3
crewai
3
memory
3
reliability
3
scalability
3
transfer-learning
3
agent-architecture
2
autogen
2
benchmarking
2
context engineering
2
distributed computing
2
distributed-systems
2
evaluation
2
exploration
2
heuristics
2
hierarchical-rl
2
hybrid systems
2
program-synthesis
2
q-learning
2
search
2
search algorithms
2
self-correction
2
slms
2
software-development
2
software-engineering
2
swarm intelligence
2
uncertainty
2
vector databases
2
a* algorithm
1
active-inference
1
actor-critic
1
adaptation
1
adaptive systems
1
adversarial search
1
agent training
1
agent-safety
1
api
1
attention-mechanisms
1
auction-theory
1
autoformalization
1
automata
1
autonomous-systems
1
bandit-algorithms
1
batch-rl
1
bayesian
1
bdi
1
behavior trees
1
behavioral-cloning
1
bellman equation
1
c51
1
catastrophic-forgetting
1
causal-inference
1
causal-reasoning
1
classical-ai
1
classical-planning
1
claude
1
claude-code
1
code review
1
code-generation
1
coding agent
1
cognitive science
1
collaboration
1
communication-protocols
1
complexity
1
composition
1
compositionality
1
consensus
1
conservative-q-learning
1
constitutional ai
1
constrained-decoding
1
constrained-mdp
1
continual-learning
1
continuous-control
1
control-theory
1
conversational ai
1
cooperative-ai
1
cooperative-game-theory
1
corrigibility
1
cpo
1
credit-assignment
1
crew-based
1
csp
1
curiosity
1
curriculum-learning
1
dag
1
dagger
1
debate
1
debugging
1
decision-theory
1
decision-transformer
1
deep-learning
1
deepeval
1
deliberation
1
design-patterns
1
developer-workflow
1
devops
1
diffusion-models
1
distributed ai
1
distributional-rl
1
dpo
1
dspy
1
dyna
1
dynamic programming
1
embeddings
1
embodied-ai
1
emergence
1
emergent-behavior
1
entropy-regularization
1
error-handling
1
ethics
1
fairness
1
fault-tolerance
1
few-shot-learning
1
formal-methods
1
frameworks
1
free-energy
1
function calling
1
future
1
game-ai
1
generative-ai
1
goal-conditioned
1
goap
1
google adk
1
grounding
1
her
1
heuristic-search
1
hierarchical planning
1
htn
1
human-in-the-loop
1
ide
1
imitation-learning
1
information retrieval
1
intent-classification
1
interactive-systems
1
interoperability
1
interruptibility
1
intrinsic-motivation
1
inverse-rl
1
knowledge-distillation
1
knowledge-representation
1
lagrangian
1
language-models
1
learning
1
learning-from-demonstrations
1
lifelong-learning
1
marl
1
maximum-entropy
1
mcp
1
mcts
1
mean-field-games
1
memory systems
1
meta-cognition
1
meta-learning
1
meta-programming
1
metrics
1
mmlu
1
model-based
1
model-compression
1
monitoring
1
nash equilibrium
1
neural-networks
1
neural-symbolic
1
neuroscience
1
nlp
1
o1
1
observability
1
offline-rl
1
openai
1
opponent-modeling
1
optimization
1
options-framework
1
paired
1
parallelism
1
pathfinding
1
pddl
1
perception
1
pipelines
1
plr
1
plugin architecture
1
poker
1
policy-gradients
1
pomdps
1
preference-learning
1
problem solving
1
prompt chaining
1
prompt-optimization
1
prompting
1
qr-dqn
1
quality-assurance
1
react
1
recursive-reasoning
1
reflexion
1
repl
1
resilience
1
retrieval
1
reward engineering
1
reward-learning
1
reward-machines
1
reward-modeling
1
risk-sensitive
1
rlhf
1
robotic-planning
1
robotics
1
role-specialization
1
saas
1
sac
1
safety
1
sample-efficiency
1
scaling
1
scaling laws
1
self-improvement
1
self-organization
1
self-play
1
self-refinement
1
semantic search
1
semantic-routing
1
shapley-values
1
skill-learning
1
soft-actor-critic
1
source-control
1
sparse-rewards
1
spec-driven-development
1
specialization
1
stanford
1
startups
1
state-management
1
strategy
1
strips
1
structured-output
1
subgoals
1
subscription platform
1
successor-representations
1
swarm
1
swe-agent
1
symbolic ai
1
symbolic-reasoning
1
system design
1
systems-architecture
1
task decomposition
1
task-allocation
1
task-scheduling
1
task-specification
1
td learning
1
temporal-abstraction
1
test-time compute
1
theory-of-mind
1
training
1
trajectory-optimization
1
transformers
1
tree of thoughts
1
validation
1
value functions
1
vector embeddings
1
verification
1
vision-language
1
windsurf
1
workflow
1
workflow-orchestration
1