mhtirogla
Home
Systems
API
Pricing
About
Log in
← Back
Home
›
Systems
›
Agentic AI
deep-research
deep research agent
Claude Research
System
Techniques · 14
Primitives · 67
deep-research
Citation grounding
agentic-ai · medium: Attaching answer spans to retrieved source passages and verifying each claim is supported
Prompt injection defense
agentic-ai · medium: Treat every untrusted string as data, track where values came from, and make tool calls and rendered output depend on provenance, not on what the model says.
›
Durable workflow execution
distributed · medium: Ordinary code made crash-proof by logging every side-effect result and replaying the code from that log; activities run at least once, workflow logic must be deterministic.
›
HTML main-text extraction
machine-learning · medium: Decode bytes, tolerate broken markup, drop non-content nodes and score text blocks by length and link density to keep the main run, with headings, metadata and offsets for citation.
›
LLM-as-judge
machine-learning · medium: Grade open-ended outputs with a language model under a rubric, then correct its known biases by order swapping, voting and calibration against human labels.
›
Near-duplicate detection with MinHa…
machine-learning · medium: Estimate set Jaccard similarity from k min-hashes and find similar pairs with banded LSH buckets; the standard dedup for web crawls, training corpora and sequence collections.
›
Cross-encoder reranking
search-sort · medium: Re-score the top-k candidates of a cheap first stage with a model that reads query and candidate together; more accurate than separate embeddings, but one model call per pair.
›
Text chunking
machine-learning · low: Cut documents into token-bounded pieces along structure boundaries, keeping offsets and section paths, so each piece embeds well and can be cited.
›
Agent loop
agentic-ai · unknown:
Context window management
agentic-ai · low: Keep an agent's growing history inside the model's window by truncating, clearing and summarizing old turns in a cheap-to-lossy ladder, at turn boundaries.
›
Prompt caching
agentic-ai · low: Reuse the attention keys/values of a repeated prompt prefix, so an agent's growing context is prefilled once and later turns pay only for the new tokens.
›
Subagent orchestration
agentic-ai · unknown:
Task planning
agentic-ai · unknown:
Embeddings
machine-learning · low: A learned table mapping discrete ids to dense vectors: gather forward, sparse scatter-add backward, row-wise optimizers to keep huge tables cheap.
›
PDF text extraction
machine-learning · low: Rebuild words, lines, columns and reading order from the glyph positions a born-digital PDF stores, and route pages without usable text to OCR.
›
BM25 ranking
search-sort · low: The standard lexical relevance score: IDF-weighted term frequency with saturation (k1) and length normalization (b); default in Lucene, Elasticsearch and SQLite FTS5.
›
Hybrid search and rank fusion
search-sort · low: Merge a keyword (BM25) result list and a vector (ANN) list into one ranking, by ranks (RRF) or by normalized scores (convex combination).
›
Query expansion
search-sort · low: Rewriting queries with synonyms, pseudo-relevance feedback or LLM-generated variants (multi-query, HyDE)
Pdf object model parsing
storage · low: PDF xref tables, object streams, content stream operators and incremental updates
Fuzzy string matching
search-sort · low: Edit distance, Jaro-Winkler and trigram indexes for approximate name and address matching
Html sanitization
security · low: Allowlist-based HTML sanitizing of untrusted markup
Least privilege and isolation
security · low: Assume every component will be compromised and limit what it can then reach: narrow identities, separate accounts, sandboxed processes.
›
Record replay
distributed · low: Record every nondeterministic input (time, randomness, I/O, model and tool outputs, per-tick player input) and re-execute deterministically for debugging, replays and state rebuild
+ 7 more techniques
+ 51 more primitives
System
Techniques · 14
Primitives · 67
deep-research
Citation grounding
agentic-ai · medium: Attaching answer spans to retrieved source passages and verifying each claim is supported
Prompt injection defense
agentic-ai · medium: Treat every untrusted string as data, track where values came from, and make tool calls and rendered output depend on provenance, not on what the model says.
›
Durable workflow execution
distributed · medium: Ordinary code made crash-proof by logging every side-effect result and replaying the code from that log; activities run at least once, workflow logic must be deterministic.
›
HTML main-text extraction
machine-learning · medium: Decode bytes, tolerate broken markup, drop non-content nodes and score text blocks by length and link density to keep the main run, with headings, metadata and offsets for citation.
›
LLM-as-judge
machine-learning · medium: Grade open-ended outputs with a language model under a rubric, then correct its known biases by order swapping, voting and calibration against human labels.
›
Near-duplicate detection with MinHa…
machine-learning · medium: Estimate set Jaccard similarity from k min-hashes and find similar pairs with banded LSH buckets; the standard dedup for web crawls, training corpora and sequence collections.
›
Cross-encoder reranking
search-sort · medium: Re-score the top-k candidates of a cheap first stage with a model that reads query and candidate together; more accurate than separate embeddings, but one model call per pair.
›
Durable job queue
distributed · medium: Persisted tasks that workers lease for a visibility timeout, ack on success and retry with backoff; at-least-once execution that survives worker and queue crashes.
›
Html parsing
graphics · medium: WHATWG HTML tokenizer state machine and tree construction with error recovery
Text classification
machine-learning · medium: Assign one or more labels to a text; climb a ladder from regexes to linear models on n-grams, embeddings, fine-tuned encoders and LLM prompts, only as far as the data and budget demand.
›
Taint tracking
security · medium: Track untrusted sources to sensitive sinks through dataflow
Unicode confusables
security · medium: UTS #39 maps every string to a "skeleton" so look-alikes collide, and restricts script mixing so most spoofs never get registered.
›
Dataflow analysis
compilers · medium: Compute a fact per program point (live variables, reaching definitions, available expressions) by iterating transfer functions over the CFG to a fixed point.
›
Parser error recovery
compilers · medium: Recover from syntax errors via synchronization tokens and error nodes to keep a full tree
Text chunking
machine-learning · low: Cut documents into token-bounded pieces along structure boundaries, keeping offsets and section paths, so each piece embeds well and can be cited.
›
Agent loop
agentic-ai · unknown:
Context window management
agentic-ai · low: Keep an agent's growing history inside the model's window by truncating, clearing and summarizing old turns in a cheap-to-lossy ladder, at turn boundaries.
›
Prompt caching
agentic-ai · low: Reuse the attention keys/values of a repeated prompt prefix, so an agent's growing context is prefilled once and later turns pay only for the new tokens.
›
Subagent orchestration
agentic-ai · unknown:
Task planning
agentic-ai · unknown:
Embeddings
machine-learning · low: A learned table mapping discrete ids to dense vectors: gather forward, sparse scatter-add backward, row-wise optimizers to keep huge tables cheap.
›
PDF text extraction
machine-learning · low: Rebuild words, lines, columns and reading order from the glyph positions a born-digital PDF stores, and route pages without usable text to OCR.
›
BM25 ranking
search-sort · low: The standard lexical relevance score: IDF-weighted term frequency with saturation (k1) and length normalization (b); default in Lucene, Elasticsearch and SQLite FTS5.
›
Hybrid search and rank fusion
search-sort · low: Merge a keyword (BM25) result list and a vector (ANN) list into one ranking, by ranks (RRF) or by normalized scores (convex combination).
›
Query expansion
search-sort · low: Rewriting queries with synonyms, pseudo-relevance feedback or LLM-generated variants (multi-query, HyDE)
Pdf object model parsing
storage · low: PDF xref tables, object streams, content stream operators and incremental updates
Fuzzy string matching
search-sort · low: Edit distance, Jaro-Winkler and trigram indexes for approximate name and address matching
Html sanitization
security · low: Allowlist-based HTML sanitizing of untrusted markup
Least privilege and isolation
security · low: Assume every component will be compromised and limit what it can then reach: narrow identities, separate accounts, sandboxed processes.
›
Record replay
distributed · low: Record every nondeterministic input (time, randomness, I/O, model and tool outputs, per-tick player input) and re-execute deterministically for debugging, replays and state rebuild
Event sourcing
finance · low: Persist state changes as an append-only stream of immutable events per entity; current state is a fold over them, guarded by expected-version appends.
›
Hierarchical timing wheel
systems · low: Timers bucketed by expiry into wheels of slots, coarser wheels for far deadlines: O(1) insert and cancel for millions of timeouts.
›
Text normalization
machine-learning · low: Rewrite messy text into one canonical form for matchers and models, or into spoken words for speech output (and back), keeping a map to the original offsets.
›
Unicode text tokenization for search
search-sort · low: Turn multilingual text into index terms: segment words (UAX 29 style, CJK bigrams), normalize, case-fold and accent-fold, identically at index and query time.
›
Token sampling
ml-training · low: Turn a vector of scores into one chosen item with temperature, top-k, top-p, min-p, repetition penalties and a seed.
›
Annotator agreement
statistics · low: Inter-annotator agreement measures: Cohen and Fleiss kappa, Krippendorff alpha, gold-question accuracy
Bradley terry model
statistics · low: Pairwise comparison model P(i beats j)=s_i/(s_i+s_j); MLE fit, link to Elo and reward models
Fast hash functions
data-structures · low: Non-cryptographic hashes built from 64×64→128-bit multiplies and xor-shifts; pick by key size, trust level and whether the hash is persisted.
›
Rolling hash
data-structures · low: Rabin-Karp polynomial rolling hashes and winnowing for substring fingerprints and document matching
Swiss table
data-structures · low: Open-addressing hash table that filters 8-16 slots at once with 1-byte hash tags and SIMD, giving fast lookups at 87.5 % load.
›
Byte-pair encoding (BPE) tokenizati…
machine-learning · low: Learn a subword vocabulary by repeatedly merging the most frequent adjacent pair; byte-level BPE encodes any input losslessly with 32k-200k tokens.
›
Transformer block
ml-training · low: The decoder-only pre-norm block (attention plus MLP on a residual stream) behind every modern LLM, with exact shapes, parameter, FLOP and KV-cache counts.
›
Top-k selection
search-sort · low: Keep the k best of n items without sorting all n - bounded min-heap for streams, quickselect for arrays, threshold pruning to skip most items.
›
Dead-letter queue
distributed · low: A side queue for messages that keep failing: after N delivery attempts or a permanent error, park them with the reason so the main queue keeps moving.
›
Leases
distributed · low: A lock that expires on its own: bounded-time ownership that survives crashes and partitions, given bounded clock drift and fencing tokens on writes.
›
Idempotency keys
finance · low: Client-chosen unique key per logical operation, stored with a request fingerprint and the final response, so retries replay the first result instead of acting twice.
›
Write-ahead log
storage · low: Append each change to a checksummed sequential log and fsync it before touching data pages; the basis of crash durability in nearly every database.
›
Exponential backoff with jitter
systems · low: Retry after delays that grow geometrically and are randomized, so failed clients spread out instead of hammering a recovering service in synchronized waves.
›
Radix trie
data-structures · low: Compressed prefix tree for path routing, domain matching and prefix lookups
String interning
data-structures · low: Store each distinct string once and refer to it by id
Calibration
machine-learning · low: Make predicted probabilities match observed frequencies: measure with ECE, fix post hoc with temperature, Platt or isotonic scaling on held-out data.
›
Linear and logistic regression
machine-learning · low: Fit a weighted sum of features to a number (least squares) or a probability (logistic); the baseline every model must beat.
›
Sanitizers
security · low: ASan/UBSan/TSan shadow memory and instrumentation to catch memory bugs
Control-flow graph
compilers · low: Split a linear instruction list into basic blocks and connect them by jumps; the graph every optimizer, SSA builder and dataflow pass walks.
›
Topological sort
graphs · low: Order the vertices of a DAG so every edge points forward; the core of build systems, schedulers and dependency resolution, with cycle detection for free.
›
Recursive-descent parsing
compilers · low: Hand-written top-down parser with one function per grammar rule; simple, fast, with full control over error messages and recovery.
›
Edit distance
search-sort · low: Levenshtein/Damerau distance by DP, bit-parallel Myers variant
Constrained decoding
agentic-ai · low: Force LLM output to match a regex, JSON schema or grammar by masking, at every step, the tokens that would leave the language.
›
Tool calling
agentic-ai · low: The model emits a structured call (id, name, JSON arguments) instead of prose; your code validates, runs it and returns a result tagged with the same id.
›
Reference counting
compilers · low: Keep a count of owners in each object, free it when the count hits zero; deterministic and local, but pays on every copy and leaks cycles.
›
d-ary heap
data-structures · low: Array heap with d children per node (d = 4 typical): half the binary heap's depth, siblings in one cache line, faster priority queues.
›
Fencing tokens
distributed · low: A number that grows with every lock grant and is checked by the protected resource, so a paused ex-holder's late write is rejected.
›
BFS and DFS
graphs · low: The two basic graph traversals; BFS gives hop distances and levels, DFS gives discovery/finish order for cycles, components and topological order.
›
CRC32C checksums
hardware-os · low: The Castagnoli CRC-32 with dedicated instructions on x86 (SSE4.2) and ARMv8. It is the standard fast integrity check for storage blocks, logs and network frames.
›
fsync, O_DSYNC and O_DIRECT
hardware-os · low: What fsync, fdatasync, O_DSYNC, O_DIRECT and F_FULLFSYNC really guarantee on Linux and macOS, and the exact call sequences for crash-safe files.
›
SIMD programming
hardware-os · low: Process 4-16 lanes per instruction with AVX2, AVX-512 or NEON via Rust std::arch, with runtime dispatch and a portable fallback.
›
Loss functions
machine-learning · low: The scalar a model minimizes: cross-entropy for classes and tokens, MSE or Huber for values, each with a stable form and simple gradient.
›
AdamW
ml-training · low: Adam's per-parameter adaptive steps with weight decay applied directly to the weights; the default optimizer for transformers and LLM pretraining.
›
Paged KV cache
ml-training · low: Store each sequence's attention keys/values in fixed-size blocks mapped through a block table, like virtual memory pages; near-zero fragmentation and copy-on-write sharing.
›
Reverse-mode automatic differentiat…
ml-training · low: Record the forward computation on a tape, then sweep it backwards once to get the gradient of a scalar loss for all inputs.
›
Json rpc
networking · low: JSON-RPC 2.0 requests, notifications and batching
L-BFGS
numerics · low: Quasi-Newton minimizer that approximates the inverse Hessian from the last m gradient differences via the two-loop recursion; O(m·n) memory and work per step.
›
LU and Cholesky factorization
numerics · low: Factor A = PLU (any square matrix, partial pivoting) or A = LLᵀ (SPD) once in O(n³), then solve each right-hand side in O(n²).
›
PRNGs (PCG, xoshiro)
numerics · low: Small, fast, statistically strong non-cryptographic generators: PCG32 and xoshiro256**, with seeding, parallel streams and unbiased ranges.
›
Sparse matrices (CSR)
numerics · low: Compressed sparse row stores only nonzeros as row pointers, column indices and values; SpMV streams them once, so it is memory-bandwidth bound.
›
Finite state transducer
search-sort · low: Minimal acyclic FST mapping sorted keys to values; compact term dictionaries with prefix/fuzzy search
Cryptographic hashes (SHA-2, BLAKE3)
security · low: Collision-resistant fingerprints of data; SHA-256 for interoperability, BLAKE3 for speed, HMAC/HKDF for keyed uses.
›
JSON Schema validation
security · low: Compile a JSON Schema once, then check every untrusted document against it, within hard size and depth limits, and report failures as JSON Pointers.
›
Optimistic concurrency control
storage · low: Run transactions without locks, record what they read, and validate at commit that nothing changed; fastest when conflicts are rare.
›
LRU and CLOCK
systems · low: LRU evicts the least recently used entry via hash map plus linked list; CLOCK approximates it with a reference bit, so hits take no lock.
›
Slab allocator
systems · low: Pre-carve pages into equal-size slots per size class with an in-place free list: O(1) alloc and free, no external fragmentation, cache-warm reuse.
›
Copy for AI
Similar systems
Share the most building blocks with this one.
rag
43 %
ai-co-scientist
36 %
support-agent
30 %
agent-memory
29 %
automated-ai-research
25 %