mhtirogla
Home
Systems
API
Pricing
About
Log in
← Back
Home
›
Systems
›
Agentic AI
voice-agent
real-time voice agent
phone support bots
System
Techniques · 23
Primitives · 90
voice-agent
Deterministic simulation testing
distributed · medium: Run the whole system in one thread under a seeded scheduler with simulated network, disk and clock, so every failure replays from its seed.
›
Primary-backup replication
distributed · medium: One node orders all writes and ships them to standbys; the acknowledgement rule (none, one, all) sets what a crash loses, and an external arbiter decides who takes over.
›
Chunked streaming attention
machine-learning · medium: Chunk-limited attention masks with cached left context so encoders (Conformer, Whisper-style) run streaming at bounded latency
Neural vocoders
machine-learning · medium: Generating waveforms from mel/acoustic features (HiFi-GAN, WaveNet-style, Vocos)
RNN transducer (RNN-T)
machine-learning · medium: Streaming sequence model that sums all monotone alignments in a frame-by-label lattice and conditions each label on earlier ones.
›
Acoustic echo cancellation
media · medium: Adaptive filter (NLMS/frequency-domain) removing far-end echo from the microphone signal
Jitter buffer
media · medium: A receiver-side buffer holds packets just long enough, a delay tracked from recent arrivals, to reorder them and hand out media at a steady rate.
›
RTP and RTCP
media · low: RTP stamps each media packet with sequence number, media-clock timestamp and source ID; RTCP reports loss, jitter, round trip and clock mapping within a bandwidth cap.
›
Voice activity detection
machine-learning · low: Per-frame speech/non-speech decision with smoothing, from an energy threshold over a tracked noise floor up to small neural nets.
›
Agent loop
agentic-ai · unknown:
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.
›
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.
›
Hdr histogram
data-structures · low: Log-linear bucketed histograms with bounded relative error for latency percentiles
Process supervision
hardware-os · low: A parent process starts services, reaps their exits and restarts them under a delay and burst-limit policy, then stops them with SIGTERM before SIGKILL.
›
End of turn detection
machine-learning · low: Deciding when a speaker has finished (silence plus prosody/semantic models) to start a reply with low latency
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.
›
Opus codec
media · low: Opus audio codec: SILK/CELT modes, frame sizes, bitrate and FEC settings for real-time voice
Sip signaling
media · low: SIP call setup, dialogs, SDP offer/answer and registrar/proxy routing
Continuous batching
ml-training · low: Schedule LLM inference per iteration, not per request; finished sequences leave and new ones join the running batch every step, which keeps the GPU full.
›
Server-sent events
networking · low: One long-lived HTTP response carries text events one way; each event may carry an id, so a reconnecting client names its last one and the server resumes.
›
WebSockets
networking · low: Full-duplex message framing over one upgraded HTTP connection; the standard way to push real-time data to browsers.
›
Mutual TLS
security · low: TLS where the client also proves a certificate key, so every connection carries a verified, rotatable machine identity.
›
Graceful draining
systems · low: On a termination signal, stop taking new work, finish in-flight work until a deadline, tell clients to reconnect elsewhere, then exit; clients resume from a token.
›
+ 16 more techniques
+ 74 more primitives
System
Techniques · 23
Primitives · 90
voice-agent
Deterministic simulation testing
distributed · medium: Run the whole system in one thread under a seeded scheduler with simulated network, disk and clock, so every failure replays from its seed.
›
Primary-backup replication
distributed · medium: One node orders all writes and ships them to standbys; the acknowledgement rule (none, one, all) sets what a crash loses, and an external arbiter decides who takes over.
›
Chunked streaming attention
machine-learning · medium: Chunk-limited attention masks with cached left context so encoders (Conformer, Whisper-style) run streaming at bounded latency
Neural vocoders
machine-learning · medium: Generating waveforms from mel/acoustic features (HiFi-GAN, WaveNet-style, Vocos)
RNN transducer (RNN-T)
machine-learning · medium: Streaming sequence model that sums all monotone alignments in a frame-by-label lattice and conditions each label on earlier ones.
›
Acoustic echo cancellation
media · medium: Adaptive filter (NLMS/frequency-domain) removing far-end echo from the microphone signal
Jitter buffer
media · medium: A receiver-side buffer holds packets just long enough, a delay tracked from recent arrivals, to reorder them and hand out media at a steady rate.
›
Neural audio codecs
media · medium: Encoder plus residual vector quantization plus decoder (EnCodec/SoundStream) giving discrete audio tokens
Noise suppression
media · medium: Spectral gain estimation (Wiener/RNN) to remove background noise from speech
Webrtc
media · medium: WebRTC stack: ICE, DTLS-SRTP, RTP, congestion control and data channels for real-time media
Beam search decoding
ml-training · medium: Keep the k best partial sequences by summed log-probability at every step, set finished ones aside, and return the best (n-best) by a length-normalised score.
›
Coverage-guided fuzzing
security · medium: Mutate inputs, run an instrumented target, and keep any input that reaches a new code edge; feedback turns blind guessing into incremental search.
›
Sample rate conversion
signal-processing · medium: Polyphase and windowed-sinc resampling; asynchronous rate conversion for clock drift
Point-in-time recovery
storage · medium: Periodic base backups plus a continuously archived change log let you rebuild the state as of any instant, then branch from there.
›
Delta debugging
compilers · medium: Ddmin minimization of failing inputs or change sets
Fault injection
distributed · medium: Inject latency, errors, kills and partitions via proxies, netem or hooks
NAT traversal (STUN, ICE, TURN)
media · medium: Learn your public address with STUN, swap candidate addresses over signalling, test pairs with ICE checks, and fall back to a TURN relay if no direct path works.
›
Packet loss concealment
media · medium: Synthesize missing audio frames from prior signal (pitch repetition, neural PLC)
Delay based congestion control
networking · medium: One-way delay gradient estimation for real-time media (GCC, transport-cc)
TLS 1.3
security · medium: The standard encrypted, authenticated transport; one round trip, only forward-secret AEAD suites, and little left to misconfigure.
›
ARIES recovery
storage · medium: Three-pass crash recovery (analysis, redo, undo) for steal/no-force buffer pools; repeats history, then rolls back losers with compensation log records.
›
Syscall interception
security · medium: Intercept syscalls via ptrace, seccomp user notify or a user-space kernel
Buffer pool
storage · medium: The database's own page cache (frames, page table, pin counts, dirty bits, replacement) so it, not the OS, controls eviction, write order and I/O.
›
RTP and RTCP
media · low: RTP stamps each media packet with sequence number, media-clock timestamp and source ID; RTCP reports loss, jitter, round trip and clock mapping within a bandwidth cap.
›
Voice activity detection
machine-learning · low: Per-frame speech/non-speech decision with smoothing, from an energy threshold over a tracked noise floor up to small neural nets.
›
Agent loop
agentic-ai · unknown:
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.
›
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.
›
Hdr histogram
data-structures · low: Log-linear bucketed histograms with bounded relative error for latency percentiles
Process supervision
hardware-os · low: A parent process starts services, reaps their exits and restarts them under a delay and burst-limit policy, then stops them with SIGTERM before SIGKILL.
›
End of turn detection
machine-learning · low: Deciding when a speaker has finished (silence plus prosody/semantic models) to start a reply with low latency
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.
›
Opus codec
media · low: Opus audio codec: SILK/CELT modes, frame sizes, bitrate and FEC settings for real-time voice
Sip signaling
media · low: SIP call setup, dialogs, SDP offer/answer and registrar/proxy routing
Continuous batching
ml-training · low: Schedule LLM inference per iteration, not per request; finished sequences leave and new ones join the running batch every step, which keeps the GPU full.
›
Server-sent events
networking · low: One long-lived HTTP response carries text events one way; each event may carry an id, so a reconnecting client names its last one and the server resumes.
›
WebSockets
networking · low: Full-duplex message framing over one upgraded HTTP connection; the standard way to push real-time data to browsers.
›
Mutual TLS
security · low: TLS where the client also proves a certificate key, so every connection carries a verified, rotatable machine identity.
›
Graceful draining
systems · low: On a termination signal, stop taking new work, finish in-flight work until a deadline, tell clients to reconnect elsewhere, then exit; clients resume from a token.
›
Cooperative scheduling
concurrency · low: Green threads/coroutines yielding at await points on a user-space scheduler
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
PRNGs (PCG, xoshiro)
numerics · low: Small, fast, statistically strong non-cryptographic generators: PCG32 and xoshiro256**, with seeding, parallel streams and unbiased ranges.
›
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.
›
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.
›
Health checking
systems · low: Decide per backend whether to route to it using probes and real-traffic errors, with consecutive-count hysteresis, capped ejection and a panic fallback.
›
Attention variants
machine-learning · low: Multi-head, multi-query, grouped-query, sliding-window and latent attention; same softmax(QKᵀ/√d)V core, different trade-offs between quality and KV-cache size.
›
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.
›
Convolutional networks
ml-training · low: Layers that slide a small shared kernel over a grid, giving translation equivariance and few parameters; still the most compute-efficient choice for many vision tasks.
›
Short-time Fourier transform and sp…
signal-processing · low: Slide a window over a signal and FFT each frame to get a time-frequency picture; the front end of audio ML, vibration and radar analysis.
›
Recurrent networks
machine-learning · low: GRU and LSTM cells for streaming sequence models
Parameter smoothing
media · low: Per-sample ramps of control parameters to avoid zipper noise
Realtime audio callback
media · low: Allocation- and lock-free audio thread design with bounded work per buffer
Fast Fourier transform
numerics · low: Computes the DFT in O(n log n) by recursively splitting into even and odd halves; the basis of fast convolution and spectral methods.
›
IIR and FIR filters
signal-processing · low: Two ways to shape a sampled signal's spectrum: FIR (finite taps, always stable, exact linear phase) or IIR (feedback, a few coefficients, cheap but phase-distorting).
›
A/V sync and media clocks
media · low: How audio and video stay lip-synced: per-stream timebases, PTS/DTS, PCR and RTCP clock mapping, and a master clock that slave streams chase by dropping, repeating or resampling.
›
Exponential smoothing (ETS, Holt-Wi…
statistics · low: Forecast by keeping a few running states (level, trend, seasonal) updated by a fraction of each forecast error; O(1) memory per series and a strong baseline.
›
Vector quantization
compression · low: Codebook and pyramid vector quantization of coefficient vectors
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.
›
Sdp offer answer
media · low: SDP session descriptions and offer/answer negotiation
SRTP
media · low: Per-packet encryption, authentication and replay protection for RTP and RTCP that keeps the headers readable, with the packet index derived from the 16-bit sequence number.
›
Sctp protocol
networking · low: SCTP multi-streaming, multi-homing and message framing for telecom signalling
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.
›
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.
›
Code coverage instrumentation
compilers · low: Insert counters into compiled code to record which blocks, edges or lines ran; a spanning tree of the control-flow graph cuts the counters needed.
›
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.
›
Sanitizers
security · low: ASan/UBSan/TSan shadow memory and instrumentation to catch memory bugs
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.
›
Object storage
cloud · low: S3-compatible blob storage at cents per GB-month with 11 nines durability; pick by egress price, request price and latency, not by storage price alone.
›
Copy on write snapshots
storage · low: Point-in-time snapshots by sharing pages/extents and copying only on write
Failure bisection
search-sort · low: Binary search over commits, batches or inputs to isolate a failure
Transparent interception
networking · low: Redirect traffic to a local proxy (iptables TPROXY/REDIRECT, eBPF) without app changes
Network address translation
networking · low: NAT mapping tables, endpoint-independent mapping/filtering, hairpinning and port allocation
Message authentication codes (HMAC,…
security · low: A keyed short tag proving a message is unmodified and came from a key holder; pick HMAC, CMAC, KMAC or a one-time polynomial MAC by what primitive you already have.
›
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.
›
Linear predictive coding (LPC)
media · low: Predict each sample from the previous p; code only the small prediction error plus p coefficients. Core of FLAC, speech codecs and the Opus SILK layer.
›
Kalman filter
robotics · low: Optimal recursive estimator for a linear system with Gaussian noise: fuses a motion model with noisy measurements into a state estimate plus its covariance.
›
AEAD (AES-GCM, ChaCha20-Poly1305)
security · low: Authenticated encryption that encrypts and detects tampering in one call; the only kind of symmetric encryption you should use.
›
Cryptographic hashes (SHA-2, BLAKE3)
security · low: Collision-resistant fingerprints of data; SHA-256 for interoperability, BLAKE3 for speed, HMAC/HKDF for keyed uses.
›
ECDH key exchange (X25519, P-256)
security · low: Each side multiplies the other's public curve point by its own scalar and both get the same point; always validate the peer key and run the result through a KDF.
›
HKDF key derivation (extract-and-ex…
security · low: HMAC-based two-step key derivation: extract a uniform pseudorandom key from any secret, then expand it into as many context-bound keys as you need.
›
X509 certificates
security · low: Certificate chains, path validation, SANs, revocation and short-lived issuance
Ebpf
hardware-os · low: Verified in-kernel programs on hooks (kprobes, XDP, tc) with maps
Ptrace process control
hardware-os · low: Ptrace: attach, read and write registers and memory, single-step, intercept signals
Seccomp bpf
security · low: Syscall filtering with seccomp BPF programs
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.
›
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.
›
S3-FIFO
systems · low: Three FIFO queues (small, main, ghost) that evict one-hit wonders quickly and keep reused objects; low miss ratios with no list moves on hits.
›
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.
›
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.
›
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.
›
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.
›
Radix trie
data-structures · low: Compressed prefix tree for path routing, domain matching and prefix lookups
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.
›
Minimum spanning tree
graphs · low: Cheapest set of edges connecting all vertices; Kruskal sorts edges and joins components with union-find, Prim grows one tree, Boruvka merges in parallel rounds.
›
Union-find
graphs · low: Disjoint-set forest with union by size and path compression; merges sets and answers same-set queries in effectively constant time.
›
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.
›
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.
›
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.
›
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.
›
Media containers
media · low: MP4/ISO BMFF, fragmented MP4/CMAF, Matroska and MPEG-TS mux/demux
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.
›
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.
›
Json rpc
networking · low: JSON-RPC 2.0 requests, notifications and batching
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
Scalar quantization
search-sort · low: Per-dimension int8/binary quantization of vectors with rescoring
Constant time code
security · low: Writing secret-dependent code without branches or memory lookups on secrets; constant-time compare and select
Csprng
security · low: OS-backed cryptographically secure random numbers (getrandom), and when a fast PRNG is not enough
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.
›
Biquad filters
signal-processing · low: Second-order IIR sections (RBJ cookbook): low/high pass, peaking EQ; stable cascades
Copy for AI
Similar systems
Share the most building blocks with this one.
speech-to-speech-model
42 %
voice-assistant
40 %
contact-center
36 %
voip
35 %
text-to-speech
34 %