Expressions and functions

This page documents ABL’s expression language: operators, variable paths, {{}} template-string interpolation, the 43 built-in functions, and type coercion rules. Expressions are used in conditions (WHEN, CHECK, constraint rules), value assignments (SET), template interpolation ({{}}), and function calls. For rich content output formats (voice, cards, carousels, interactive actions, templates), see Rich content.

---

​

Expression syntax

​

Comparison operators

Operator	Syntax	Description
==	a == b	Equal to.
!=	a != b	Not equal to.
>	a > b	Greater than.
<	a < b	Less than.
>=	a >= b	Greater than or equal to.
<=	a <= b	Less than or equal to.
in	a IN [x,y,z]	Value is in the list.
not_in	a NOT IN [x]	Value is not in the list.
matches	a matches r	Value matches a regular expression.
contains	a contains b	String contains substring, or array contains element.
startsWith	a startsWith b	String starts with a prefix.
endsWith	a endsWith b	String ends with a suffix.

​

Logical operators

Operator	Syntax	Description
AND	a AND b	Both conditions must be true.
OR	a OR b	At least one must be true.
NOT	NOT a	Negates the condition.

Write logical operators in uppercase (AND, OR, NOT). ! is also accepted as a prefix negation.

contains, matches, startsWith, and endsWith are infix operators (a contains b), not callable functions — a condition that calls one as a bare function (CONTAINS(ani_national, "1234567890")) parses but has no matching overload, so it can never evaluate true; the compiler warns CEL_CONDITION_UNRESOLVED_CALL. Use the infix form, or the abl.* CEL method form (x.contains("y")).

​

Unary operators

Operator	Syntax	Description
NOT / !	NOT condition / !condition	Negates a condition.
IS SET	var IS SET	True if the variable is not null/undefined (empty string counts as set).
IS NOT SET	var IS NOT SET	True if the variable is null or undefined.
is_number	var is_number	True if the variable is a number.

​

Operator precedence

1. Parentheses ()
2. Unary operators (NOT, IS SET, IS NOT SET)
3. Comparison operators (==, !=, >, <, >=, <=, contains, matches)
4. AND
5. OR

Use parentheses to override default precedence:

WHEN: (status == "active" OR status == "pending") AND amount > 0

​

Quoting a condition

A WHEN value — in HANDOFF, ON_RETURN WHEN, ESCALATE triggers, COMPLETE, and hook WHEN/RESPOND branches — is unwrapped from its quotes and evaluated as a condition whenever it contains a condition operator: ==, !=, <, >, &&, ||, !, IS [NOT] SET, contains, matches, startsWith, endsWith, in, or a function call. So WHEN: "dispute == true" and WHEN: dispute == true are the same condition. A quoted value with none of these — a natural-language phrase such as WHEN: "task done" — stays a quoted literal string, which most deterministic evaluators treat as always-truthy.

Write a genuinely deterministic condition either unquoted or quoted-with-an-operator; reserve a bare quoted phrase for constructs that intentionally accept free text (a prompt-only/semantic condition). A deterministic routing or escalation entry’s when must be an operator expression regardless of quoting — see Deterministic-only routing.

​

Variable paths and dot notation

Reference variables using dot notation to access nested values.

user.name                  # Access nested property
user.addresses[0].city     # Array index access
acctResult.status          # Tool result field

​

Path resolution rules

• The evaluator looks up the full path in the session context.
• The Platform resolves each segment left to right: user.address.city resolves user, then address on the result, then city.
• If any segment resolves to null or undefined, the entire path resolves to undefined.
• Array access uses bracket notation: items[0], items[2].name.

​

Template strings

Template strings use {{}} syntax for variable interpolation within RESPOND, summary, and other string properties — including inside a TEMPLATES: block body:

RESPOND: "Hello, {{customer_name}}! Your balance is {{available_balance}}."

​

Conditional sections

Templates support conditional rendering with {{#if}}...{{/if}}:

RESPOND: |
  Transfer complete.
  {{#if fx_rate}}Exchange rate: {{fx_rate}}{{/if}}
  Estimated arrival: {{estimated_arrival}}.

​

Function calls in templates

You can call built-in functions within template strings:

SET:
  formatted_balance = FORMAT_CURRENCY(available_balance, "USD")
RESPOND: "Your balance is {{formatted_balance}}."

​

Built-in function reference

ABL provides 36 built-in functions organized into seven categories (plus the CEL-only content-analysis helpers described below). All functions are called with FUNCTION_NAME(arg1, arg2, ...) syntax. Function names are uppercase.

​

Math functions

Function	Signature	Description	Example
ADD	ADD(a, b) -> number	Add two numbers.	ADD(2, 3) returns 5
SUB	SUB(a, b) -> number	Subtract b from a.	SUB(10, 3) returns 7
MUL	MUL(a, b) -> number	Multiply two numbers.	MUL(4, 5) returns 20
DIV	DIV(a, b) -> number	Divide a by b. Returns null for division by zero.	DIV(10, 2) returns 5
ROUND	ROUND(n, decimals?) -> number	Round to specified decimal places. Default: 0.	ROUND(3.14159, 2) returns 3.14
ABS	ABS(n) -> number	Absolute value.	ABS(-5) returns 5
MIN	MIN(a, b) -> number	Return the smaller of two numbers.	MIN(3, 7) returns 3
MAX	MAX(a, b) -> number	Return the larger of two numbers.	MAX(3, 7) returns 7

Math functions coerce string arguments to numbers automatically: ADD("2", "3") returns 5.

​

String functions

Function	Signature	Description	Example
UPPER	UPPER(s) -> string	Convert to uppercase.	UPPER("hello") returns "HELLO"
LOWER	LOWER(s) -> string	Convert to lowercase.	LOWER("HELLO") returns "hello"
TRIM	TRIM(s) -> string	Strip leading/trailing whitespace.	TRIM(" hi ") returns "hi"
SUBSTRING	SUBSTRING(s, start, end?) -> string	Extract a substring.	SUBSTRING("hello", 0, 3) returns "hel"
REPLACE	REPLACE(s, find, repl) -> string	Replace all occurrences.	REPLACE("a,b,c", ",", "-") returns "a-b-c"
SPLIT	SPLIT(s, delimiter) -> string[]	Split string into array.	SPLIT("a,b,c", ",") returns ["a","b","c"]
JOIN	JOIN(arr, delimiter) -> string	Join array into string.	JOIN(["a","b"], ", ") returns "a, b"
PAD_START	PAD_START(s, length, char?) -> string	Left-pad to specified length.	PAD_START("42", 6, "0") returns "000042"
PAD_END	PAD_END(s, length, char?) -> string	Right-pad to specified length.	PAD_END("42", 6, "0") returns "420000"
REPEAT	REPEAT(s, count) -> string	Repeat string N times.	REPEAT("*", 4) returns "****"
REGEX_REPLACE	REGEX_REPLACE(text, pattern, replacement) -> string	RE2-backed replace-all; $1-$9 in replacement insert capture groups. Matching is single-pass, so ^/\b anchor against the original string, not partial replacement output. Returns text unchanged on an invalid pattern — never throws.	REGEX_REPLACE("00123", "^0", "") returns "0123"
REGEX_EXTRACT	REGEX_EXTRACT(text, pattern, group?) -> string | null	First match, or capture group group when given. Returns null when nothing matches or the pattern is invalid — never throws.	REGEX_EXTRACT("order-4821", "\\d+") returns "4821"

The string functions gracefully handle null and undefined and return an empty string: UPPER(null) returns "".

To prevent memory issues, the limit on string output is 100,000 characters.

​

Identity-matching functions

These compare what a caller actually said against a stored value — they are deterministic similarity scoring, not a semantic/model judgment, built for voice identity verification (see Write authority for a READONLY field that stores the result).

Function	Signature	Description
MATCH_SCORE	MATCH_SCORE(said, stored, kind?) -> number	Similarity 0-100 between said and stored. Returns -1 when there’s nothing to judge — a missing/empty value, a PII vault token, or an input over 1,024 characters. -1 is below every threshold, so MATCH_SCORE(...) >= 70 fails closed.
MATCHES	MATCHES(said, stored, kind?) -> boolean	Pass/fail form of MATCH_SCORE on the platform’s own match bands (below). Not a regex test — the infix a MATCHES "pattern" operator (see Comparison operators) is the regex form.
MATCH_RESULT	MATCH_RESULT(said, stored, kind?) -> string	"match", "retry" (a tight near-miss only), "mismatch", or "missing".

kind is optional — omitted, it defaults to text (unchanged behavior, no warning) — and otherwise one of:

kind	Meaning
name / person_name	A personal name, scored part-by-part on how it sounds.
email	An email address, read from spoken forms (“at the rate”, “dot”, spelled letters).
address	A street address, read part by part in any order.
phone / digits	Digits only, with spoken-digit and trunk/country-code handling (phone), or an exact digit-for-digit identifier like a member number (digits — no national-number truncation).
text	Plain text similarity (the default).
auto	Detects the kind from the stored value’s shape: an @ with a dotted domain → email; mostly digits with 7-10 digits or a leading + → phone; digits only, under 7 or 11+ with no + → digits; a house-number-plus-street-type pattern → address; 2-4 capitalized words → person_name; otherwise text. An explicit kind (including "text") is never auto-detected — "auto" only applies when you pass it.
exact	Turns off every voice allowance: matches only after Unicode normalization, trimming, case-folding, and collapsing spaces/trailing punctuation — “Steven” does not match “Stephen”.

Platform-owned match bands (authors never pick a threshold):

Kind	match	retry	mismatch
phone, digits	every digit matches (100)	exactly one digit slip, or two neighbouring digits swapped (50)	anything else
email, name/person_name, address, text	score ≥ 70	score 50-69 (a tight near-miss only)	score < 50

A -1 score (nothing to judge) always reports "missing".

The guiding principle: values that sound the same cannot be told apart by a caller (speech-to-text just picks a spelling), so they score as a "match" — only values that sound genuinely different can fail. For example email compares the domain by sound but matches its ending exactly (kore.ai is not kore.com); person_name matches common respellings (Jon/John, Steven/Stephen) and scores a near-same name (Ahmed/Ahmad) as "retry", never a straight mismatch, while a genuinely different name (Mark/Mary) is a "mismatch"; address reads house/unit letters and matches street words that sound alike. The matcher reads the value itself, not the sentence around it — filler words (“no”, “sorry”, “I mean”) are not stripped, so an answer that contains them alongside the correct value still fails to match as written.

said must be the extracted field (for example supplied_email), not the raw caller utterance. An extracted field is written by the model and may already hold the stored value (for example, after a lookup tool returned the profile) — a match on the field alone does not prove the caller actually said it. A rule that grants access on a match should also confirm the caller’s own words contained the value.

The function MATCHES(said, stored[, kind]) and the infix operator a MATCHES "pattern" are unrelated — do not mix up their second argument. Writing MATCHES(supplied, "^gold$") (the function form with a regex-shaped literal) is almost certainly meant to be the infix form supplied MATCHES "^gold$", and the compiler warns MATCHES_FUNCTION_REGEX_LITERAL. Conversely, writing tier MATCHES "gold" (the infix form with a plain literal) is true whenever "gold" appears anywhere in tier as a substring — not a fuzzy spoken-answer comparison — and the compiler warns MATCHES_INFIX_LITERAL_AMBIGUOUS since this is easy to mean the other way.

​

Formatting functions

Function	Signature	Description	Example
MASK	MASK(s, pattern, char?) -> string	Mask a string. See Mask Patterns below.	MASK("4111111111111111", "last4") returns "************1111"
FORMAT_CURRENCY	FORMAT_CURRENCY(n, currency, locale?) -> string	Format a number as currency.	FORMAT_CURRENCY(1234.5, "USD") returns "$1,234.50"
FORMAT_DATE	FORMAT_DATE(d, format, tz?) -> string	Format a date string.	FORMAT_DATE("2024-03-15T10:30:00Z", "YYYY-MM-DD") returns "2024-03-15"
ORDINAL	ORDINAL(n) -> string	Convert number to ordinal string.	ORDINAL(1) returns "1st", ORDINAL(22) returns "22nd"

The mask patterns are explained below.

Pattern	Behavior	Example result
last4	Mask all characters except the last 4.	"************1111"
first4	Mask all characters except the first 4.	"4111************"
N*N	Show N chars at start, mask middle, show N at end.	MASK(s, "4*4") shows 4+4

The default mask character is *. Pass a third argument to use a different character: MASK(ssn, "last4", "x").

The date format uses the following notations:

Token	Description	Example
YYYY	Four-digit year	2024
MM	Two-digit month	03
DD	Two-digit day	15
HH	Two-digit hour (24h)	10
mm	Two-digit minute	30
ss	Two-digit second	00

Example: FORMAT_DATE("2024-03-15T10:30:00Z", "YYYY-MM-DD HH:mm") returns "2024-03-15 10:30".

FORMAT_DATE formats in UTC by default — a date-time string without an explicit offset is interpreted as UTC, so the output is deterministic regardless of where the runtime executes. Pass an optional IANA timezone name as the third argument to format in that zone instead:

FORMAT_DATE("2024-03-15T10:30:00Z", "YYYY-MM-DD HH:mm", "America/New_York")  # "2024-03-15 06:30"

An unrecognized timezone falls back to UTC.

​

Type checking and coercion functions

Function	Signature	Description	Example
IS_ARRAY	IS_ARRAY(x) -> boolean	True if the value is an array.	IS_ARRAY([1,2]) returns true
IS_NUMBER	IS_NUMBER(x) -> boolean	True if the value is a number (not NaN).	IS_NUMBER(42) returns true
IS_STRING	IS_STRING(x) -> boolean	True if the value is a string.	IS_STRING("hi") returns true
TO_NUMBER	TO_NUMBER(x) -> number	null	Convert to number. Returns null if conversion fails. TO_NUMBER("42") returns 42
TO_STRING	TO_STRING(x) -> string	Convert to string. Returns "" for null/undefined.	TO_STRING(42) returns "42"

​

Array functions

Function	Signature	Description	Example
LENGTH	LENGTH(x) -> number	Array length or string length. Returns 0 for other types.	LENGTH([1,2,3]) returns 3
ARRAY_FIND	ARRAY_FIND(arr, field, value) -> object	null	Find first element where field == value. ARRAY_FIND(users, "id", 42) returns the matching object
ARRAY_FIND_INDEX	ARRAY_FIND_INDEX(arr, field, value) -> number	Find index of first match. Returns -1 if not found.	ARRAY_FIND_INDEX(items, "type", "b") returns the index

​

Object functions

Function	Signature	Description	Example
OBJECT_KEYS	OBJECT_KEYS(obj) -> string[]	Return array of object keys.	OBJECT_KEYS({a:1, b:2}) returns ["a","b"]
OBJECT_VALUES	OBJECT_VALUES(obj) -> any[]	Return array of object values.	OBJECT_VALUES({a:1, b:2}) returns [1, 2]
OBJECT_MERGE	OBJECT_MERGE(obj1, obj2, ...) -> object	Merge objects. Right-side values win on conflict.	OBJECT_MERGE({a:1}, {b:2}) returns {a:1, b:2}

OBJECT_KEYS and OBJECT_VALUES return an empty array for non-object inputs (null, arrays, strings).

OBJECT_MERGE accepts any number of arguments and skips non-object values.

​

Utility functions

Function	Signature	Description	Example
COALESCE	COALESCE(a, b, ...) -> any	Return the first non-null, non-undefined value. Returns null if all arguments are null.	COALESCE(null, undefined, "hello") returns "hello"
FIRST_NON_EMPTY	FIRST_NON_EMPTY(a, b, ...) -> any	Return the first value that is not null, undefined, "", or blank. Unlike COALESCE, it skips an empty/blank string.	FIRST_NON_EMPTY("", null, "hello") returns "hello"
IF	IF(cond, a, b) -> any	Eager conditional — both a and b are evaluated regardless of cond. Use the ternary cond ? a : b for lazy evaluation.	IF(amount > 100, "high", "low")
NOW	NOW() -> string	Return the current timestamp as an ISO 8601 string.	NOW() returns "2024-03-15T10:30:00.000Z"
UNIQUE_ID	UNIQUE_ID(length?) -> string	Generate a random alphanumeric string. Default length: 6.	UNIQUE_ID(12) returns "aB3kM9pQ2xLw"

COALESCE considers 0 and false as valid (non-null) values: COALESCE(0, "fallback") returns 0.

UNIQUE_ID generates a random alphanumeric string suitable for reference numbers. It is not cryptographically secure — do not use it for tokens or secrets.

​

Content-analysis functions (CEL guardrails)

CEL-based guardrail checks have access to an additional abl.* namespace of content-analysis helpers:

Function	Description
abl.contains_pii(text)	True if the text contains PII.
abl.detect_pii(text)	Structured PII detection result.
abl.redact_pii(text)	Returns the text with PII redacted.
abl.matches_pattern(text, pattern)	Regex match (RE2-backed). Patterns are limited to 500 characters. See Pattern limits.
abl.not_matches_pattern(text, pattern)	Negation of matches_pattern.
abl.word_count(text)	Word count.
abl.sentence_count(text)	Sentence count.
abl.contains_url(text)	True if the text contains a URL.
abl.contains_email(text)	True if the text contains an email address.
abl.contains_code(text)	True if the text contains a fenced code block.
abl.pii_equal(left, right)	True if two PII-vault tokens hold the same underlying value. See below.

​

Pattern limits

abl.matches_pattern and abl.not_matches_pattern run on the RE2 engine.

• Each pattern can be at most 500 characters and must use RE2 syntax. RE2 has no backreferences or lookarounds.
• A pattern outside these limits never matches. abl.not_matches_pattern is then true for every input. Validation warns with CEL_MATCH_PATTERN_REJECTED.
• To use a longer pattern, split it into several calls joined with ||, or with && for abl.not_matches_pattern.
• The checked text is scanned up to 100,000 characters. Text past that length is not scanned.

In CEL expressions the core functions above are also available under the abl. namespace with lowercase names (for example, abl.upper(x)), and CEL-native operators (&&, ||, !, %, in, ternary ? :) and macros (size(), has()) can be used.

abl.pii_equal(left, right) compares two values without ever exposing the underlying plaintext to the expression — both left and right must be live PII-vault tokens (the opaque form a PII-classified value takes once captured, for example, via a sensitive: true GATHER field), and the comparison happens inside the vault itself. Values are canonicalized before comparing (email lowercased/trimmed, phone/SSN/credit-card digits-only, etc.), so abl.pii_equal(session.data.values.email, caller_provided_email) matches [e-mail] against [e-mail].

CHECK: abl.pii_equal(session.data.values.email, caller_provided_email)
ON_FAIL: identity_mismatch

If either operand isn’t a live vault token for the same PII type — missing, expired, or a plain string — abl.pii_equal throws rather than returning false. This is deliberate: silently returning false on a fault would make !abl.pii_equal(x, y) evaluate true on a comparison that couldn’t actually be performed. Guard against this with IS SET checks on both operands before comparing, or route the resulting evaluation error through your usual error handling.

​

Nested function calls

Functions can be nested as arguments to other functions:

SET:
  result = ADD(MUL(2, 3), SUB(10, 4))     # Returns 12
  name = UPPER(TRIM("  hello  "))           # Returns "HELLO"
  fallback = COALESCE(user.lastName, "Guest")

Nesting is limited to a maximum depth of 32 to prevent stack overflow.

​

Using expressions in ABL

​

In conditions (WHEN, CHECK, constraint rules)

WHEN: user.age >= 18 AND user.verified == true
CHECK: amount <= available_balance
- REQUIRE sanctions_clear == true

​

Long boolean conditions

Ordinary boolean conditions can combine AND, OR, and NOT beyond the original 4,096-unit CEL limit. The extended path accepts up to 65,536 prepared UTF-16 source units, 4,096 syntax nodes, and 64 nesting levels. Each indivisible comparison, call, or ternary stays limited to 4,096 units. CEL evaluates the complete parsed expression and keeps precedence and short-circuit order.

Short conditions, strict checkpoint conditions, PII comparisons, and scalar SET evaluation keep their existing protections. A supported long rule can now match where the old fallback disagreed. No migration is required. An unsupported expression produces the non-blocking warning CEL_EXPRESSION_LIMIT, with its agent, path, and prepared length.

​

Size limits for conditions and regex patterns

The same limits apply to every condition: step IF / WHEN branches, HANDOFF and DELEGATE WHEN, COMPLETE, constraints, hooks, and guardrail checks.

What	Limit
A whole condition, with parts joined by AND, OR, and NOT	65,536 characters
Syntax parts in one condition	4,096
Nesting depth in one condition	64 levels
One part: a single comparison, function call, list (x in [...]), or conditional (? :)	4,096 characters
A whole condition that compares protected (PII) values, or a checkpoint condition	4,096 characters
A computed value, such as a SET value	4,096 characters
One regex pattern in abl.matches_pattern, abl.not_matches_pattern, or x MATCHES "…"	500 characters, RE2

Lengths are counted in characters after ABL syntax is converted to CEL, so they can differ slightly from what you typed. HANDOFF and DELEGATE WHEN evaluate each top-level OR / AND alternative on its own, so the limits apply to each alternative.

A condition or pattern over a limit does not stop the agent and is not an error:

• At publish, the compiler warns: CEL_EXPRESSION_LIMIT for a condition and CEL_MATCH_PATTERN_REJECTED for a pattern written as text. Studio shows up to three of these warnings as toasts after you publish an agent, with a “+N more” note. A pattern held in a variable can only be checked at run time.
• At run time, a pattern over the limit matches nothing: abl.matches_pattern is false and abl.not_matches_pattern is true for every input. A condition over the limit is not evaluated as written. Most conditions fall back to a simpler evaluator that can return a different result. Hook CALL / RESPOND guards, checkpoint conditions, and PII comparisons fail closed. In step branches and in HANDOFF / DELEGATE WHEN, the session trace records a warning event with code condition_limit_reached, the reason, and the length.

To stay within the limits, split long rules into shorter parts joined with OR / AND (|| / &&):

# A pattern over 500 characters: split it into several calls.
WHEN: abl.matches_pattern(input, "refund|chargeback|money back") || abl.matches_pattern(input, "cancel order|cancel my order")

# For abl.not_matches_pattern, join the calls with &&.
WHEN: abl.not_matches_pattern(input, "password|pin") && abl.not_matches_pattern(input, "card number|cvv")

​

Comments in conditions

On condition surfaces that accept line comments, // outside a complete string starts a comment through the end of the line. Comment text does not add variables, operators, or WHEN, BEFORE, or IMPLIES clauses. A quoted URL, or // inside an escaped, raw, bytes, or triple-quoted string, stays literal. YAML enabled_when keeps its separate single-line scalar restriction.

A condition that contains only comments is invalid for these constructs:

• A constraint requirement or applicability gate.
• A HANDOFF or DELEGATE WHEN or ENABLED_WHEN.
• A conditional GATHER activation.

An omitted condition and an ordinary blank value keep the policy of the construct that owns them. Malformed expressions receive compiler diagnostics.

​

In SET assignments

SET:
  balance_formatted = FORMAT_CURRENCY(available_balance, "USD")
  wire_reference = UNIQUE_ID(12)
  greeting = COALESCE(user.name, "valued customer")

​

Missing paths in value expressions

A value expression computes a value for a CALL argument (WITH or a named inline argument), a tool PROCESS mapping, a TRANSFORM MAP field, or a SET. Inside one, a key that is missing from a record reads as null wherever it appears, including inside COALESCE, a ternary, an object or list literal, and arithmetic. So COALESCE(order.list.items, fallback) falls through to fallback when order has no list. Only the branch a ternary takes is evaluated. x IS SET over a missing nested path is false.

Value expression	Value
COALESCE(empty.list.kind, "fallback")	"fallback"
(COALESCE(empty.list.n, 0) == 0) ? 7 : 8	7
[{"orderId": "1", "x": COALESCE(empty.list.kind, "")}]	[{"orderId": "1", "x": ""}]
COALESCE(empty.list.n, 0) + 1	1
empty.list.kind IS SET ? "yes" : "no"	"no"
empty.list.kind	no value

An expression has no value in two cases:

• A single path that is not set, such as empty.list.kind on its own. A CALL argument written this way is left out of the tool input, and a MAP field has no value. Use COALESCE(path, default) when the tool needs a value.
• An expression that cannot be evaluated, such as text plus a number, a ternary whose condition is not true or false, or bracket access to a missing key (order["list"].kind). The runtime never sends a partial reading of it. The trace records a warning event that names the argument or field.

Behavior change. An expression that cannot be evaluated now sends no value instead of a partial one. Check agents that pass computed arguments to tools.

​

Types in conditions and computed values

• A conditional needs a true/false condition. In flag ? "a" : "b", flag must hold true or false. Text, a number, or a missing value is an evaluation error. Write flag == true ? "a" : "b" when flag may be missing.
• !x needs a true/false x. Write flag != true when flag may be missing.
• contains needs text or a list on the left. On text it is a substring test. On a list, an element must equal the right side. A number or an object on the left is an evaluation error.
• Arithmetic needs numbers. + also joins text to text and a list to a list.

​

When a SET value cannot be evaluated

A computed value is a function call, field read, index, conditional, comparison, logical operator, or arithmetic with an operand that is quoted text or a variable the session holds or declares. When one cannot be evaluated:

• A step SET clears the variable. A HANDOFF CONTEXT SET leaves it unchanged.
• The trace gets a warning event with code set_expression_not_evaluated. It carries field, source, outcome (no_value, or stored_expression_text under keep_text), reason (ternary_condition_not_bool, no_matching_overload, or evaluation_failed), and a hint. It never carries values or the expression text.

recent_input is a built-in available in SET contexts: the caller’s last 3 utterances, joined. input_transcript is a built-in, read-only SET value on realtime voice channels — the provider’s transcript of the current caller turn (empty when there is none). An authored session variable with either name takes precedence over the built-in.

​

In template interpolation

RESPOND: "Hello, {{customer_name}}! Balance: {{FORMAT_CURRENCY(available_balance, 'USD')}}."

​

In TRANSFORM pipelines

TRANSFORM:
  SOURCE: search_results
  AS: item
  INTO: filtered_results
  FILTER: item.price <= budget AND item.available == true
  MAP:
    name: item.hotel_name
    price: FORMAT_CURRENCY(item.price, "USD")
  SORT_BY: price ASC
  LIMIT: 5

​

Type coercion rules

The evaluator applies these coercion rules during expression evaluation:

Context	Rule
Equality (==)	null/undefined == null/undefined is true. Strings compared case-sensitively. Numbers parsed from strings.
Inequality (!=)	If either side is undefined/null, returns true.
Numeric (>, <, etc.)	Strings parsed to numbers. Booleans become 0/1. Arrays become length. Undefined becomes 0.
Truthiness (bare variable)	false, 0, "", "false", null, undefined, empty arrays, empty objects are falsy. Everything else is truthy.
IS SET / IS NOT SET	Checks for null/undefined only. Empty string IS SET.
Arithmetic (+ - * / %)	Works between a decimal session number and an integer literal, in either order, producing a decimal result (for example turn_count == followup_offer_turn + 1). Division or modulus by zero is an error — the condition does not hold — never Infinity.

---

Related articles:

• Rich content — voice configuration, format-specific output, carousels, interactive actions, and templates
• Memory and constraints — condition expressions in constraint rules, variable paths and session context
• Multi-agent and supervisor — condition syntax for WHEN clauses in routing/escalation
• Data types and utilities — types used in function signatures, lookup validation functions